# Data analysis

Data analysis is the systematic process of inspecting, cleaning, transforming, and modeling data to extract information, identify patterns, and support decision-making.

This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles.

## Hellinger Decision Trees for Density Ratio Estimation: Finite-Sample Guarantees

DevFeed: [Hellinger Decision Trees for Density Ratio Estimation: Finite-Sample Guarantees](<https://devfeed.tech/articles/hellinger-decision-trees-for-density-ratio-estimation-finite-sample-guarantees-145119.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.25936>)

Author: Ren-Rui Liu, Zheng-Chu Guo

Published: 2026-11-20T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Data analysis](<https://devfeed.tech/topics/data-analysis.md>)

Tags: [boosting](<https://devfeed.tech/tags/boosting.md>), [convergence](<https://devfeed.tech/tags/convergence.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [datasets](<https://devfeed.tech/tags/datasets.md>), [decision-trees](<https://devfeed.tech/tags/decision-trees.md>), [experiments](<https://devfeed.tech/tags/experiments.md>), [guarantees](<https://devfeed.tech/tags/guarantees.md>), [newton](<https://devfeed.tech/tags/newton.md>), [optimization](<https://devfeed.tech/tags/optimization.md>), [ratio](<https://devfeed.tech/tags/ratio.md>), [risk](<https://devfeed.tech/tags/risk.md>), [stat-ml](<https://devfeed.tech/tags/stat-ml.md>)

### AI overview

The paper estimates log density ratios directly by minimizing balanced Hellinger risk over additive ensembles of axis-aligned decision trees trained with Newton boosting, avoiding separate estimation of the underlying densities. Under stated tail and Hölder smoothness conditions and an additional assumption about progress at each boosting iteration, it gives finite-sample guarantees with an explicit rate matching the classical minimax-optimal L² function-estimation rate up to logarithmic factors. Its optimization analysis shows that a computable decrease in the second-order Taylor approximation controls the actual empirical-risk decrease, enabling guarantees for the algorithm's output without assuming an ideal empirical-risk minimizer. The abstract reports synthetic experiments consistent with predicted convergence and public-dataset experiments showing practical effectiveness.

### Source excerpt

arXiv:2611.25936v1 Announce Type: cross Abstract: Density ratios play a central role in two-sample comparison, distribution-shift adaptation, and generative-model evaluation. However, estimating a density ratio through separate estimation of the underlying densities can be unnecessarily challenging. In this paper, we develop a direct approach to the log density ratio estimation by minimizing a balanced Hellinger risk over additive ensembles of axis-aligned decision trees, trained using Newton boosting. We establish finite-sample guarantees for the estimator produced by the algorithm and derive an explicit convergence rate. Under suitable tail and H\"{o}lder smoothness conditions, together with an additional assumption on the progress made at each boosting iteration, our rate matches, up to logarithmic factors, the classical minimax-optimal $ \mathscr{L}^{2} $ rate for function estimation. A key technical contribution is an optimization analysis that exploits the special exponential structure of the Hellinger risk. In particular, we show that the decrease in the second-order Taylor approximation (which is computable) of the empirical risk controls the actual decrease in that risk, yielding a direct optimization guarantee for the boosting algorithm. This allows us to establish statistical convergence guarantees for the algorithm's output without relying on an idealized empirical-risk minimizer. Experiments on synthetic data corroborate the predicted convergence behavior, while experiments on public datasets demonstrate the practical effectiveness of the proposed estimator.

## Algorithmic Market Making Can Lead to Rough Volatility Through the Order Book

DevFeed: [Algorithmic Market Making Can Lead to Rough Volatility Through the Order Book](<https://devfeed.tech/articles/algorithmic-market-making-can-lead-to-rough-volatility-through-the-order-book-143474.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.24028>)

Author: Sai Niranjan Ramachandran

Published: 2026-11-19T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Finance](<https://devfeed.tech/topics/finance.md>), [Data analysis](<https://devfeed.tech/topics/data-analysis.md>), [Functional programming](<https://devfeed.tech/topics/functional-programming.md>)

Tags: [batch](<https://devfeed.tech/tags/batch.md>), [binance](<https://devfeed.tech/tags/binance.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [flow](<https://devfeed.tech/tags/flow.md>), [gradient](<https://devfeed.tech/tags/gradient.md>), [gradient-descent](<https://devfeed.tech/tags/gradient-descent.md>), [horizon](<https://devfeed.tech/tags/horizon.md>), [information](<https://devfeed.tech/tags/information.md>), [maker](<https://devfeed.tech/tags/maker.md>), [market-making](<https://devfeed.tech/tags/market-making.md>), [memory](<https://devfeed.tech/tags/memory.md>), [model](<https://devfeed.tech/tags/model.md>), [oracle](<https://devfeed.tech/tags/oracle.md>), [orders](<https://devfeed.tech/tags/orders.md>), [power](<https://devfeed.tech/tags/power.md>), [q-fin-mf](<https://devfeed.tech/tags/q-fin-mf.md>), [q-fin-tr](<https://devfeed.tech/tags/q-fin-tr.md>), [scaling](<https://devfeed.tech/tags/scaling.md>), [volume](<https://devfeed.tech/tags/volume.md>)

### AI overview

The paper proposes that asynchronous market makers can generate rough volatility through order-book dynamics. Each desk adjusts order distances toward oracle-supplied targets using a first-order gradient rule, acting when relevant information arrives over its own lookback horizon. Collectively, these updates resemble stochastic gradient descent with information-driven noise. In the continuum limit, book volume follows the Dean-Kawasaki equation; its fluctuations drive order flow, while varied desk horizons produce power-law memory that leads, through scaling arguments, to rough volatility. The authors report support from simulated agents and six months of Binance data comprising about 790 million orders, with Binance perpetual futures' order books consistent with the modeled changes. The abstract presents this as one mechanism, not a complete account of market behavior.

### Source excerpt

arXiv:2611.24028v1 Announce Type: new Abstract: Existing work suggests that markets can show volatility with paths rougher than those of Brownian motion. In theory this can happen when the order flow is close to instability with memory that decays as a power law. However, it is not fully clear how such order flow could arise from the predominantly algorithmic market making that characterizes order book dynamics. We show one such consistent mechanism. We treat each market maker as a desk that uses a first-order gradient rule to move the distances of its orders from the mid price toward target distances provided by an unknown oracle. We assume that distinct desks do not act synchronously in time but act whenever new information relevant to their respective oracles arrives, which each desk samples over its own characteristic lookback horizon. Across all desks the rule therefore takes the form of stochastic gradient descent (SGD) with information-driven (mini-batch) noise. In the continuum limit this update rule makes the volume of the order book follow a conservative stochastic partial differential equation (the Dean--Kawasaki equation) whose fluctuations drive the order flow. The distinct horizons of the desks further induce a persistent memory in the order flow that decays as a power law. Standard scaling arguments then lead to rough volatility. We confirm the key predictions of the model on simulated agents and on six months of Binance data with about 790 million orders. In liquid markets governed mainly by market makers, such as the perpetual futures of Binance, the order books are consistent with how our desks change the book.

## Harmonic Circuit: Chord Progression Lies in a Sparse Principal Information Flow in Symbolic Music Models

DevFeed: [Harmonic Circuit: Chord Progression Lies in a Sparse Principal Information Flow in Symbolic Music Models](<https://devfeed.tech/articles/harmonic-circuit-chord-progression-lies-in-a-sparse-principal-information-flow-in-symbolic-music-models-142798.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.24453>)

Author: Ruiji Yu, Gus Xia

Published: 2026-11-19T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>), [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Neural Network](<https://devfeed.tech/topics/neural-network.md>), [Data analysis](<https://devfeed.tech/topics/data-analysis.md>)

Tags: [algorithm](<https://devfeed.tech/tags/algorithm.md>), [behaviors](<https://devfeed.tech/tags/behaviors.md>), [circuit](<https://devfeed.tech/tags/circuit.md>), [circuits](<https://devfeed.tech/tags/circuits.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [cs-sd](<https://devfeed.tech/tags/cs-sd.md>), [discovery](<https://devfeed.tech/tags/discovery.md>), [domain](<https://devfeed.tech/tags/domain.md>), [flow](<https://devfeed.tech/tags/flow.md>), [function](<https://devfeed.tech/tags/function.md>), [functional](<https://devfeed.tech/tags/functional.md>), [generative](<https://devfeed.tech/tags/generative.md>), [information](<https://devfeed.tech/tags/information.md>), [model](<https://devfeed.tech/tags/model.md>), [models](<https://devfeed.tech/tags/models.md>), [music](<https://devfeed.tech/tags/music.md>), [natural-language-processing](<https://devfeed.tech/tags/natural-language-processing.md>), [prediction](<https://devfeed.tech/tags/prediction.md>), [root](<https://devfeed.tech/tags/root.md>), [terminal](<https://devfeed.tech/tags/terminal.md>), [validation](<https://devfeed.tech/tags/validation.md>)

### AI overview

The study identifies a sparse information-flow circuit that helps ChatMusician and MuPT predict the terminal tonic root in the classical progression I ... V -> I. Using Auto-Emergence, the authors extract a principal sub-network and report that causal interventions confirm it is a primary driver of the models' harmonic progression behavior. They describe this as the first systematic circuit-discovery study in music models.

### Source excerpt

arXiv:2611.24453v1 Announce Type: cross Abstract: Mechanistic Interpretability (MI) seeks to decode neural network computations into human-understandable logic. A core methodology in MI is circuit discovery: identifying the information flow in sub-networks that drive specific model behaviors. While circuit discovery has matured within Natural Language Processing (NLP), the interpretable circuits in music models remain largely unexplored. In this work, we identify a music-functional circuit within two symbolic music generative models: ChatMusician and MuPT. The music function we consider is the prediction of the terminal tonic root in a classical harmonic progression pattern $I \ldots V \rightarrow I$. We use the Auto-Emergence algorithm to extract a principal sparse sub-network as the identified circuit. Validation via causal intervention confirms that this identified circuit is a primary driver of harmonic progression behaviors in the symbolic music models. To our knowledge, this represents the first systematic circuit-discovery study conducted within the music domain. Our demo page is available at: https://ukiyo23rui.github.io/auto-emergence-demo/.

## Asking but Missing: Decision Coverage in Natural-Language Data Querying

DevFeed: [Asking but Missing: Decision Coverage in Natural-Language Data Querying](<https://devfeed.tech/articles/asking-but-missing-decision-coverage-in-natural-language-data-querying-142199.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.23864>)

Author: Hangle Hu, Chenyu Hou, Bin Cao, Jing Fan, Wei Luo

Published: 2026-11-19T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>), [arXiv: Software Engineering](<https://devfeed.tech/sources/arxiv-software-engineering.md>)

Topics: [Large Language Model](<https://devfeed.tech/topics/llm.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [llm-reasoning](<https://devfeed.tech/topics/llm-reasoning.md>), [Data analysis](<https://devfeed.tech/topics/data-analysis.md>)

Tags: [code-generation](<https://devfeed.tech/tags/code-generation.md>), [coverage](<https://devfeed.tech/tags/coverage.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-se](<https://devfeed.tech/tags/cs-se.md>), [data](<https://devfeed.tech/tags/data.md>), [decision](<https://devfeed.tech/tags/decision.md>), [errors](<https://devfeed.tech/tags/errors.md>), [execution](<https://devfeed.tech/tags/execution.md>), [framework](<https://devfeed.tech/tags/framework.md>), [language-models](<https://devfeed.tech/tags/language-models.md>), [natural-language](<https://devfeed.tech/tags/natural-language.md>), [querying](<https://devfeed.tech/tags/querying.md>)

### AI overview

The study finds that natural-language data querying models often fail to recognize when a question needs clarification, silently choosing an interpretation that can produce incorrect code. It calls this Underspecified Decision Completion (UDC) and introduces Grounded Code Generation (GCG), which separately diagnoses whether unresolved decisions were identified, resolved using evidence, and translated into executable code. Evaluation of 12 models on BIRD-Pandas found that answering clarification questions consistently improves execution accuracy, but substantial errors remain; the key difficulty appears to be deciding which questions to ask.

### Source excerpt

arXiv:2611.23864v1 Announce Type: cross Abstract: Large language models are increasingly used to translate natural language questions about structured data into executable programs. A fundamental challenge is recognizing when a question admits multiple computational interpretations and identifying the decisions needed to resolve them. We investigate whether language models recognize these unresolved decisions before generating code, or silently adopt assumptions that may lead to incorrect results. We refer to the latter behavior as Underspecified Decision Completion (UDC). To distinguish different causes of UDC, we introduce Grounded Code Generation (GCG), a diagnostic protocol that separates the identification of unresolved decisions, their resolution using evidence, and their translation into executable code. By examining each stage separately, we can determine where the decisions responsible for incorrect results were first missed or mishandled. We evaluate this framework on BIRD-Pandas with twelve models. The results show that answering clarification questions consistently improves execution accuracy, yet substantial errors remain. Our findings suggest that the main difficulty lies not in answering clarification questions, but in recognizing which questions need to be asked in the first place.

## From Arraignment to Resolution: Transformer Models of Court Cases

DevFeed: [From Arraignment to Resolution: Transformer Models of Court Cases](<https://devfeed.tech/articles/from-arraignment-to-resolution-transformer-models-of-court-cases-143402.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.23518>)

Author: Kory Rosen, Aron Culotta

Published: 2026-11-19T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Predictive AI](<https://devfeed.tech/topics/predictive-ai.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [Time Series](<https://devfeed.tech/topics/time-series.md>), [Data analysis](<https://devfeed.tech/topics/data-analysis.md>)

Tags: [cases](<https://devfeed.tech/tags/cases.md>), [court](<https://devfeed.tech/tags/court.md>), [cs-cl](<https://devfeed.tech/tags/cs-cl.md>), [cs-cy](<https://devfeed.tech/tags/cs-cy.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [transformer](<https://devfeed.tech/tags/transformer.md>), [transformer-models](<https://devfeed.tech/tags/transformer-models.md>)

### AI overview

The paper models court cases as event sequences to forecast the next proceeding, such as charges accepted, bond set, or a plea deal. Its transformer combines clerk-note text with structured information about defendants, prior charges, and courtroom. On thousands of cases from publicly available records in one mid-sized U.S. city, it reached 0.57 micro-F1 on a 20-class multilabel task, outperforming several baselines and performing comparably to a GRU with the same inputs. The authors present the model as a way to support oversight and help observers identify emerging issues in that jurisdiction; the excerpt does not establish performance or applicability elsewhere.

### Source excerpt

arXiv:2611.23518v1 Announce Type: cross Abstract: The criminal legal system is composed of many complex decision points, such as which charges are pursued, how bond is determined, plea deal negotiations, and sentencing. Given the profound impact of such decisions, there is a growing need to increase the transparency within this system. While prior machine learning approaches have focused on modeling single decisions (e.g., recidivism), this paper proposes a transformer-based time series model to forecast the outcome of the next proceeding in a case (e.g., charges accepted, bond set, plea deal made, etc.). By modeling a case as an event sequence, we enable a more nuanced analysis to support better oversight and understanding of decision making. We conduct an empirical analysis of thousands of cases using a newly constructed dataset derived from publicly available court records of a mid-sized U.S. city. We fit models that combine textual data from clerk notes with structured information about the defendant, prior charges, and courtroom. Our transformer model achieves $.57$ micro-F1 on a 20-class multi-label task, a significant improvement over several baselines and comparable to a GRU trained on the same input. We demonstrate how the model can be used to provide insights into decision-making and help court observers identify emerging issues within the jurisdiction studied.

## Simplify Brand Awareness Analysis With Fivetran Data Models | Blog | Fivetran

DevFeed: [Simplify Brand Awareness Analysis With Fivetran Data Models | Blog | Fivetran](<https://devfeed.tech/articles/simplify-brand-awareness-analysis-with-fivetran-data-models-blog-fivetran-141338.md>)

Original publisher: [Read original article](<https://wf.fivetran.com/blog/simplify-brand-awareness-analysis-with-fivetran-data-models>)

Author: Joe Markiewicz

Published: 2026-11-18T06:13:15Z

Content type: article

Language: en

Sources: [Fivetran Blog](<https://devfeed.tech/sources/fivetran-blog.md>)

Topics: [Data analysis](<https://devfeed.tech/topics/data-analysis.md>), [Data pipelines](<https://devfeed.tech/topics/data-pipelines.md>), [etl](<https://devfeed.tech/topics/etl.md>), [data-engineering](<https://devfeed.tech/topics/data-engineering.md>), [Instagram](<https://devfeed.tech/topics/instagram.md>)

Tags: [advertising](<https://devfeed.tech/tags/advertising.md>), [analysis](<https://devfeed.tech/tags/analysis.md>), [analytics](<https://devfeed.tech/tags/analytics.md>), [awareness](<https://devfeed.tech/tags/awareness.md>), [brand](<https://devfeed.tech/tags/brand.md>), [brand-awareness](<https://devfeed.tech/tags/brand-awareness.md>), [data](<https://devfeed.tech/tags/data.md>), [engagement](<https://devfeed.tech/tags/engagement.md>), [engagement-metrics](<https://devfeed.tech/tags/engagement-metrics.md>), [facebook](<https://devfeed.tech/tags/facebook.md>), [fivetran](<https://devfeed.tech/tags/fivetran.md>), [instagram](<https://devfeed.tech/tags/instagram.md>), [linkedin](<https://devfeed.tech/tags/linkedin.md>), [marketing-analytics](<https://devfeed.tech/tags/marketing-analytics.md>), [metrics](<https://devfeed.tech/tags/metrics.md>), [models](<https://devfeed.tech/tags/models.md>), [twitter](<https://devfeed.tech/tags/twitter.md>)

### AI overview

Fivetran's social media data model combines cleaned, tested, normalized engagement data from Facebook Pages, Instagram Business, Organic Twitter, and LinkedIn Company Pages into one schema and table. It rolls up clicks, impressions, shares, likes, and comments, supports combining multiple accounts on a connector, and helps compare engagement across profiles. Used alongside Fivetran's separate ad reporting model--which aggregates spend, clicks, and impressions across Facebook, Google, Pinterest, Bing, Twitter, and LinkedIn--analysts can compare daily reach and engagement. Both models use shared transformation logic maintained by Fivetran analytics engineers and community contributors.

### Source excerpt

Easily combine engagement metrics from Facebook, Instagram, Twitter and LinkedIn.

## Perform rapid analysis of your app platform data | Blog | Fivetran

DevFeed: [Perform rapid analysis of your app platform data | Blog | Fivetran](<https://devfeed.tech/articles/perform-rapid-analysis-of-your-app-platform-data-blog-fivetran-141335.md>)

Original publisher: [Read original article](<https://wf.fivetran.com/blog/perform-rapid-analysis-of-your-app-platform-data>)

Author: Jamie Rodriguez

Published: 2026-11-18T06:13:15Z

Content type: article

Language: en

Sources: [Fivetran Blog](<https://devfeed.tech/sources/fivetran-blog.md>)

Topics: [Data pipelines](<https://devfeed.tech/topics/data-pipelines.md>), [Google Play](<https://devfeed.tech/topics/google-play.md>), [etl](<https://devfeed.tech/topics/etl.md>), [data-engineering](<https://devfeed.tech/topics/data-engineering.md>), [Data analysis](<https://devfeed.tech/topics/data-analysis.md>)

Tags: [2022](<https://devfeed.tech/tags/2022.md>), [about](<https://devfeed.tech/tags/about.md>), [aggregation](<https://devfeed.tech/tags/aggregation.md>), [analysis](<https://devfeed.tech/tags/analysis.md>), [app](<https://devfeed.tech/tags/app.md>), [app-store](<https://devfeed.tech/tags/app-store.md>), [apple](<https://devfeed.tech/tags/apple.md>), [apple-app-store](<https://devfeed.tech/tags/apple-app-store.md>), [can](<https://devfeed.tech/tags/can.md>), [data](<https://devfeed.tech/tags/data.md>), [fivetran](<https://devfeed.tech/tags/fivetran.md>), [google](<https://devfeed.tech/tags/google.md>), [google-play](<https://devfeed.tech/tags/google-play.md>), [model](<https://devfeed.tech/tags/model.md>), [platform](<https://devfeed.tech/tags/platform.md>), [play](<https://devfeed.tech/tags/play.md>), [rapid](<https://devfeed.tech/tags/rapid.md>), [reporting](<https://devfeed.tech/tags/reporting.md>), [store](<https://devfeed.tech/tags/store.md>), [with](<https://devfeed.tech/tags/with.md>)

### AI overview

Fivetran's App Reporting data models standardize Google Play and Apple App Store connector data into a unified schema, aggregating app activity daily by app and across country, OS version, app version, traffic source, and device. The models are intended to reduce the need for teams to learn and join numerous normalized source tables. They include a data dictionary and model lineage graph. With Fivetran Transformations for dbt Core, integrated scheduling (available as of February 2022) runs the reporting model after connector syncs complete, so the resulting models use the latest synced data.

### Source excerpt

With Fivetran's new App Reporting data model, you can easily roll your Apple App Store and Google Play data into a unified schema for seamless reporting.

## How to Build a Modern Data Stack From the Ground Up | Blog | Fivetran

DevFeed: [How to Build a Modern Data Stack From the Ground Up | Blog | Fivetran](<https://devfeed.tech/articles/how-to-build-a-modern-data-stack-from-the-ground-up-blog-fivetran-141324.md>)

Original publisher: [Read original article](<https://wf.fivetran.com/blog/how-to-build-a-modern-data-stack-from-the-ground-up>)

Author: Fivetran

Published: 2026-11-18T06:13:15Z

Content type: tutorial

Language: en

Sources: [Fivetran Blog](<https://devfeed.tech/sources/fivetran-blog.md>)

Topics: [analytics stack](<https://devfeed.tech/topics/analytics-stack.md>), [Analytics Pipeline](<https://devfeed.tech/topics/analytics-pipeline.md>), [Data pipelines](<https://devfeed.tech/topics/data-pipelines.md>), [elt](<https://devfeed.tech/topics/elt.md>), [DataOps](<https://devfeed.tech/topics/dataops.md>), [Data serialization](<https://devfeed.tech/topics/data-serialization.md>), [Data analysis](<https://devfeed.tech/topics/data-analysis.md>)

Tags: [analysis](<https://devfeed.tech/tags/analysis.md>), [analytics](<https://devfeed.tech/tags/analytics.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [bi-tools](<https://devfeed.tech/tags/bi-tools.md>), [business-intelligence](<https://devfeed.tech/tags/business-intelligence.md>), [business-logic](<https://devfeed.tech/tags/business-logic.md>), [cloud](<https://devfeed.tech/tags/cloud.md>), [data](<https://devfeed.tech/tags/data.md>), [data-driven](<https://devfeed.tech/tags/data-driven.md>), [data-ingestion](<https://devfeed.tech/tags/data-ingestion.md>), [data-lake](<https://devfeed.tech/tags/data-lake.md>), [data-platforms](<https://devfeed.tech/tags/data-platforms.md>), [data-quality](<https://devfeed.tech/tags/data-quality.md>), [data-stack](<https://devfeed.tech/tags/data-stack.md>), [data-warehouse](<https://devfeed.tech/tags/data-warehouse.md>), [dbt](<https://devfeed.tech/tags/dbt.md>), [decision-making](<https://devfeed.tech/tags/decision-making.md>), [fivetran](<https://devfeed.tech/tags/fivetran.md>), [modern-data-stack](<https://devfeed.tech/tags/modern-data-stack.md>), [plan](<https://devfeed.tech/tags/plan.md>)

### AI overview

Build the stack around a defined analytics use case: identify the data needed, then choose an ingestion tool that connects to those sources. Centralize data in a warehouse and consider a data lake for historical data; use transformation tools such as dbt with connectors such as Fivetran to prepare data for reporting. Keep business logic consistent and models representative of the real world. Choose a BI tool based on the tradeoff that matters most, such as usability or scalability, and consult the technical team to maintain a cohesive strategy. The article emphasizes data quality throughout: validate at ingestion and transformation stages, test continuously, and promote to production only when confident the data will not mislead users.

### Source excerpt

A data architecture expert gives a crash course on moving analytics to the cloud -- including a step-by-step plan to ensure success.

## How data-driven strategies can reverse the Great Resignation | Blog | Fivetran

DevFeed: [How data-driven strategies can reverse the Great Resignation | Blog | Fivetran](<https://devfeed.tech/articles/how-data-driven-strategies-can-reverse-the-great-resignation-blog-fivetran-141322.md>)

Original publisher: [Read original article](<https://wf.fivetran.com/blog/how-data-driven-strategies-can-reverse-the-great-resignation>)

Author: Fivetran

Published: 2026-11-18T06:13:15Z

Content type: article

Language: en

Sources: [Fivetran Blog](<https://devfeed.tech/sources/fivetran-blog.md>)

Topics: [Data analysis](<https://devfeed.tech/topics/data-analysis.md>), [Data pipelines](<https://devfeed.tech/topics/data-pipelines.md>), [business-intelligence](<https://devfeed.tech/topics/business-intelligence.md>), [Data visualization](<https://devfeed.tech/topics/data-visualization.md>)

Tags: [analytics](<https://devfeed.tech/tags/analytics.md>), [ats](<https://devfeed.tech/tags/ats.md>), [bi](<https://devfeed.tech/tags/bi.md>), [business-intelligence](<https://devfeed.tech/tags/business-intelligence.md>), [cloud](<https://devfeed.tech/tags/cloud.md>), [cloud-based](<https://devfeed.tech/tags/cloud-based.md>), [cloud-data-platforms](<https://devfeed.tech/tags/cloud-data-platforms.md>), [dashboards](<https://devfeed.tech/tags/dashboards.md>), [data-analysis](<https://devfeed.tech/tags/data-analysis.md>), [data-analytics](<https://devfeed.tech/tags/data-analytics.md>), [data-driven](<https://devfeed.tech/tags/data-driven.md>), [data-pipelines](<https://devfeed.tech/tags/data-pipelines.md>), [data-stack](<https://devfeed.tech/tags/data-stack.md>), [diversity](<https://devfeed.tech/tags/diversity.md>), [diversity-and-inclusion](<https://devfeed.tech/tags/diversity-and-inclusion.md>), [employee](<https://devfeed.tech/tags/employee.md>), [pain](<https://devfeed.tech/tags/pain.md>), [people](<https://devfeed.tech/tags/people.md>), [talent](<https://devfeed.tech/tags/talent.md>), [top](<https://devfeed.tech/tags/top.md>)

### AI overview

People analytics can help HR identify employee pain points and intervene to improve retention, though the article presents these approaches as opportunities rather than guaranteed results. It recommends analyzing compensation and benefits against relevant benchmarks, tracking diversity through recruiting and tenure data, and using employee relationship maps to spot weak connections. Sentiment analysis, including automated staff surveys, can help identify employees who may leave so HR can respond proactively. These methods depend on integrating HR data sources such as HRIS and making the data available for analysis; the excerpt also describes ATS, dashboards, data warehouses and BI software as parts of the HR analytics landscape.

### Source excerpt

People analytics can help you understand employee pain points and take steps to retain top talent.

## How to Develop a Data-Driven Marketing Culture | Blog | Fivetran

DevFeed: [How to Develop a Data-Driven Marketing Culture | Blog | Fivetran](<https://devfeed.tech/articles/how-to-develop-a-data-driven-marketing-culture-blog-fivetran-141326.md>)

Original publisher: [Read original article](<https://wf.fivetran.com/blog/how-to-develop-a-data-driven-marketing-culture>)

Author: Cat Origitano

Published: 2026-11-18T06:13:15Z

Content type: tutorial

Language: en

Sources: [Fivetran Blog](<https://devfeed.tech/sources/fivetran-blog.md>)

Topics: [business-intelligence](<https://devfeed.tech/topics/business-intelligence.md>), [Data analysis](<https://devfeed.tech/topics/data-analysis.md>), [Data pipelines](<https://devfeed.tech/topics/data-pipelines.md>), [etl](<https://devfeed.tech/topics/etl.md>), [Data Quality](<https://devfeed.tech/topics/data-quality.md>)

Tags: [2022](<https://devfeed.tech/tags/2022.md>), [actions](<https://devfeed.tech/tags/actions.md>), [ads](<https://devfeed.tech/tags/ads.md>), [advertising](<https://devfeed.tech/tags/advertising.md>), [agile](<https://devfeed.tech/tags/agile.md>), [analysis](<https://devfeed.tech/tags/analysis.md>), [analysts](<https://devfeed.tech/tags/analysts.md>), [analytics](<https://devfeed.tech/tags/analytics.md>), [analyze](<https://devfeed.tech/tags/analyze.md>), [blog](<https://devfeed.tech/tags/blog.md>), [culture](<https://devfeed.tech/tags/culture.md>), [data](<https://devfeed.tech/tags/data.md>), [data-driven](<https://devfeed.tech/tags/data-driven.md>), [develop](<https://devfeed.tech/tags/develop.md>), [fivetran](<https://devfeed.tech/tags/fivetran.md>), [help](<https://devfeed.tech/tags/help.md>), [how-to](<https://devfeed.tech/tags/how-to.md>), [marketing](<https://devfeed.tech/tags/marketing.md>), [skills](<https://devfeed.tech/tags/skills.md>), [team](<https://devfeed.tech/tags/team.md>)

### AI overview

The article argues that data-driven marketing requires organizational change alongside analytics tools. As third-party cookies disappear and first-party data remains scattered across teams, it recommends setting measurable goals for data culture, securing leadership support, holding teams accountable for evidence-based decisions, and sharing lessons from wins and failures. Practical steps include reducing silos through embedded or rotating analysts, assessing marketers' skills and planning training, and ensuring analytics cover six source categories: email, CRM, paid digital advertising, organic social and digital, conversions, and website or engagement analytics. For cross-platform analysis, it recommends a modern data stack: source platforms, an automated pipeline such as Fivetran, a cloud warehouse such as Snowflake, and a BI tool such as Looker or Tableau. This can replace error-prone, stale manual spreadsheet merging, though the article presents centralization as a foundation rather than a guarantee of effective decisions.

### Source excerpt

Help your team develop the appropriate skills to win in the age of data-driven marketing.

## Why You Should Attend the Modern Data Stack Conference EMEA | Blog | Fivetran

DevFeed: [Why You Should Attend the Modern Data Stack Conference EMEA | Blog | Fivetran](<https://devfeed.tech/articles/why-you-should-attend-the-modern-data-stack-conference-emea-blog-fivetran-141299.md>)

Original publisher: [Read original article](<https://wf.fivetran.com/blog/attend-modern-data-stack-emea-2021>)

Author: Fivetran

Published: 2026-11-18T06:13:15Z

Content type: news

Language: en

Sources: [Fivetran Blog](<https://devfeed.tech/sources/fivetran-blog.md>)

Topics: [analytics stack](<https://devfeed.tech/topics/analytics-stack.md>), [Data analysis](<https://devfeed.tech/topics/data-analysis.md>), [Data Management](<https://devfeed.tech/topics/data-management.md>)

Tags: [accelerate](<https://devfeed.tech/tags/accelerate.md>), [adopting](<https://devfeed.tech/tags/adopting.md>), [alex](<https://devfeed.tech/tags/alex.md>), [allows](<https://devfeed.tech/tags/allows.md>), [amazing](<https://devfeed.tech/tags/amazing.md>), [amazon](<https://devfeed.tech/tags/amazon.md>), [analytics](<https://devfeed.tech/tags/analytics.md>), [business](<https://devfeed.tech/tags/business.md>), [conference](<https://devfeed.tech/tags/conference.md>), [data](<https://devfeed.tech/tags/data.md>), [data-stack](<https://devfeed.tech/tags/data-stack.md>), [emea](<https://devfeed.tech/tags/emea.md>), [fivetran](<https://devfeed.tech/tags/fivetran.md>), [growth](<https://devfeed.tech/tags/growth.md>), [innovation](<https://devfeed.tech/tags/innovation.md>), [leveraging](<https://devfeed.tech/tags/leveraging.md>), [modern](<https://devfeed.tech/tags/modern.md>), [modern-data](<https://devfeed.tech/tags/modern-data.md>), [modern-data-stack](<https://devfeed.tech/tags/modern-data-stack.md>), [stack](<https://devfeed.tech/tags/stack.md>)

### AI overview

The free, fully online Modern Data Stack Conference EMEA is presented as a way to learn how automated, cloud-based data tools can simplify collection and analysis, speed time to insight, and reduce reliance on maintaining traditional on-premise systems. Its stated focus is comparing the modern data stack with traditional approaches and showing how to implement it. The listed program includes speakers from Snowflake and Capgemini and panels on topics such as building a modern data stack, data-driven decisions, BI modernization, customer views, and using data for good, with organizations including The Guardian, Douglas, and Onfido. These are the excerpt's stated aims and program details; it does not provide evidence of event outcomes.

### Source excerpt

The modern data stack is transforming analytics -- discover how business leaders are leveraging it to drive innovation and growth.

## Analysis: Fivetran Is the Fastest-Growing Cloud ELT Provider | Blog | Fivetran

DevFeed: [Analysis: Fivetran Is the Fastest-Growing Cloud ELT Provider | Blog | Fivetran](<https://devfeed.tech/articles/analysis-fivetran-is-the-fastest-growing-cloud-elt-provider-blog-fivetran-141312.md>)

Original publisher: [Read original article](<https://wf.fivetran.com/blog/fivetran-is-fastest-growing-cloud-elt-provider>)

Author: Fivetran

Published: 2026-11-18T06:13:15Z

Content type: article

Language: en

Sources: [Fivetran Blog](<https://devfeed.tech/sources/fivetran-blog.md>)

Topics: [elt](<https://devfeed.tech/topics/elt.md>), [Data pipelines](<https://devfeed.tech/topics/data-pipelines.md>), [data transformation](<https://devfeed.tech/topics/data-transformation.md>), [Data analysis](<https://devfeed.tech/topics/data-analysis.md>), [Amazon Redshift](<https://devfeed.tech/topics/amazon-redshift.md>), [BigQuery](<https://devfeed.tech/topics/bigquery.md>)

Tags: [analysis](<https://devfeed.tech/tags/analysis.md>), [analytics](<https://devfeed.tech/tags/analytics.md>), [automation](<https://devfeed.tech/tags/automation.md>), [bigquery](<https://devfeed.tech/tags/bigquery.md>), [cloud](<https://devfeed.tech/tags/cloud.md>), [data-ingestion](<https://devfeed.tech/tags/data-ingestion.md>), [data-integration](<https://devfeed.tech/tags/data-integration.md>), [data-movement](<https://devfeed.tech/tags/data-movement.md>), [data-pipelines](<https://devfeed.tech/tags/data-pipelines.md>), [data-teams](<https://devfeed.tech/tags/data-teams.md>), [dbt](<https://devfeed.tech/tags/dbt.md>), [elt](<https://devfeed.tech/tags/elt.md>), [fivetran](<https://devfeed.tech/tags/fivetran.md>), [gartner](<https://devfeed.tech/tags/gartner.md>)

### AI overview

The text attributes Fivetran's growth to managed cloud data ingestion and ease of use. It quotes Gartner's 2020 market-share report, which says Fivetran nearly doubled revenue from 2019 to 2020 and identifies it as a vendor of choice for moving data from popular SaaS applications and databases into cloud warehouses. The described service uses prebuilt connectors, self-healing pipelines, minimal infrastructure management, and automatic normalization. It also offers in-warehouse SQL transformations powered by dbt, with version control, testing, and documentation. Gartner is quoted as calling this a more complete offering that could support future enterprise adoption and revenue growth.

### Source excerpt

Gartner recognizes Fivetran as the "vendor of choice" for enterprises looking to modernize their data infrastructure.

## OICycle: Observe, Infer, and Intervene Cycle for Belief-State Learning in Longitudinal Clinical Decision Making

DevFeed: [OICycle: Observe, Infer, and Intervene Cycle for Belief-State Learning in Longitudinal Clinical Decision Making](<https://devfeed.tech/articles/oicycle-observe-infer-and-intervene-cycle-for-belief-state-learning-in-longitudinal-clinical-decision-making-140083.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.22826>)

Author: Jitindra Fartiyal, Pedro Freire, Sergei K. Turitsyn, Sergei G. Solovski

Published: 2026-11-18T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>), [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [decision-making](<https://devfeed.tech/topics/decision-making.md>), [Data analysis](<https://devfeed.tech/topics/data-analysis.md>)

Tags: [adaptive](<https://devfeed.tech/tags/adaptive.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [decision](<https://devfeed.tech/tags/decision.md>), [decision-making](<https://devfeed.tech/tags/decision-making.md>), [diagnostic](<https://devfeed.tech/tags/diagnostic.md>), [electronic-health-records](<https://devfeed.tech/tags/electronic-health-records.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [gaussian](<https://devfeed.tech/tags/gaussian.md>), [health](<https://devfeed.tech/tags/health.md>), [history](<https://devfeed.tech/tags/history.md>), [hospital](<https://devfeed.tech/tags/hospital.md>), [intervene](<https://devfeed.tech/tags/intervene.md>), [irregular](<https://devfeed.tech/tags/irregular.md>), [laboratory](<https://devfeed.tech/tags/laboratory.md>), [learning](<https://devfeed.tech/tags/learning.md>), [markov](<https://devfeed.tech/tags/markov.md>), [model](<https://devfeed.tech/tags/model.md>), [multimodal](<https://devfeed.tech/tags/multimodal.md>), [next](<https://devfeed.tech/tags/next.md>), [state](<https://devfeed.tech/tags/state.md>)

### AI overview

OICycle learns a stochastic Gaussian belief state from longitudinal clinical episodes, updating it by combining a sample of the prior belief with new multimodal observations and the intervention that produced them. It is trained to predict the next clinician intervention, time to the next episode, and next-episode mortality. On a benchmark of 72,075 admissions drawn from MIMIC-IV, MIMIC-IV-Note, and MIMIC-CXR, it outperformed an otherwise identical history-free model on adaptive recall for next intervention (0.347 vs. 0.253), macro-F1 for time to next episode (0.351 vs. 0.293), and macro-F1 for next-episode mortality (0.649 vs. 0.585). The reported benefit of history is concentrated in interventions whose ordering depends on prior findings.

### Source excerpt

arXiv:2611.22826v1 Announce Type: new Abstract: Clinical care is a closed loop: clinicians observe partial evidence, infer the patient's state, and intervene, and each intervention determines what is observed next. This makes clinical decision making a partially observable Markov decision process (POMDP), in which a belief over a latent patient state must be updated from irregular, multimodal, and incomplete records. Yet most deep clinical models predict from a single snapshot or from coarsely aggregated history, while POMDP-based clinical methods need hand-specified discrete state spaces and transition models that real electronic health records cannot supply. We introduce OICycle (Observe, Infer, and Intervene Cycle), which learns a stochastic belief state directly from retrospective trajectories. At every episode, a learned recurrent operator fuses a sample of the previous belief with the new multimodal observations and the intervention that produced them. The resulting Gaussian belief is trained to predict clinicians' next interventions, the time to the next episode, and next-episode mortality. To enable reproducible evaluation, we release a benchmark derived from MIMIC-IV, MIMIC-IV-Note, and MIMIC-CXR that organizes 72,075 hospital admissions (5.4M laboratory, microbiology, radiology, prescription, and note records) into temporally ordered therapeutic--diagnostic episodes. Compared with an otherwise identical history-free model, OICycle improves next-intervention adaptive recall from 0.253 to 0.347, time-to-next-episode macro-F1 from 0.293 to 0.351, and next-episode mortality macro-F1 from 0.585 to 0.649. Analysis shows that the learned belief encodes intervention type and trajectory position and evolves smoothly across episodes, and that the benefit of history is concentrated in interventions whose ordering depends on prior findings.

## One pool, many targets: a conservation layer and what archival data can identify

DevFeed: [One pool, many targets: a conservation layer and what archival data can identify](<https://devfeed.tech/articles/one-pool-many-targets-a-conservation-layer-and-what-archival-data-can-identify-141614.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2610.00445>)

Author: Zahra Khodagholi, Niloofar Yousefi

Published: 2026-11-18T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [Predictive AI](<https://devfeed.tech/topics/predictive-ai.md>), [Data analysis](<https://devfeed.tech/topics/data-analysis.md>)

Tags: [approximation](<https://devfeed.tech/tags/approximation.md>), [bootstrap](<https://devfeed.tech/tags/bootstrap.md>), [competition](<https://devfeed.tech/tags/competition.md>), [compression](<https://devfeed.tech/tags/compression.md>), [constraint](<https://devfeed.tech/tags/constraint.md>), [context](<https://devfeed.tech/tags/context.md>), [contribution](<https://devfeed.tech/tags/contribution.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [experiments](<https://devfeed.tech/tags/experiments.md>), [faster](<https://devfeed.tech/tags/faster.md>), [independent](<https://devfeed.tech/tags/independent.md>), [invariance](<https://devfeed.tech/tags/invariance.md>), [layer](<https://devfeed.tech/tags/layer.md>), [permutation](<https://devfeed.tech/tags/permutation.md>), [pool](<https://devfeed.tech/tags/pool.md>), [rank](<https://devfeed.tech/tags/rank.md>), [scalar](<https://devfeed.tech/tags/scalar.md>), [unique](<https://devfeed.tech/tags/unique.md>)

### AI overview

The paper proposes a differentiable equilibrium layer that enforces conservation of a finite guide-loaded RISC pool through a scalar equation with a unique positive root and exact implicit gradients. Its analysis shows that, within one construct at one dose, fractional-occupancy rankings cannot distinguish equilibrium from independent scoring, leaving dose and cross-context comparisons as tests. In archival off-target data, corrected affinities associate weakly with measured repression, but paired permutation and construct-cluster bootstrap analyses do not establish added predictive value for coupling; the reported surviving difference is 0.0026 and favors independent scoring. Dose fits are heterogeneous and often violate the model's superlinear exponent constraint, so they do not identify the competition parameter. Saturable competitor-set compression preserves both accuracy targets on held-out guide families but is not faster at the measured size.

### Source excerpt

arXiv:2610.00445v2 Announce Type: replace Abstract: Pairwise guide-transcript scores do not enforce conservation of a finite guide-loaded RISC pool when they are interpreted independently as occupancies. We formulate a differentiable scalar equilibrium layer: one conservation equation with a unique positive root and exact implicit gradients. It yields a redistribution theorem, a qualified high-resource limit, an analysis of the retrieval approximation, and a conditional rank-invariance result: within one construct at one dose, rankings by fractional occupancy cannot distinguish equilibrium from independent scoring. We therefore audit the two experiments that proposition leaves open, dose and cross-context, on archival off-target data. Corrected thermodynamic affinities associate weakly with measured repression in the direction a working predictor requires, but a paired permutation test and a construct-cluster bootstrap do not establish added predictive value from the coupling: what survives their differing permutation-null baselines is 0.0026, which is 2.55 paired-null standard deviations from that baseline (p=0.010) and favours independent scoring. The dose fits are heterogeneous and frequently violate the model-implied exponent constraint, which is superlinear rather than sublinear, so these data do not identify the competition parameter. A saturable compression of the competitor set holds both accuracy targets on held-out guide families but is not faster at the size measured. The contribution is a reusable conservation operator and the experimental information needed to test it. Code, result files and the data manifest: https://github.com/shadi97kh/One-Pool-Many-Targets

## EDA: Observe, Verify, and Assess for Evidence-Grounded Multimodal Depression Analysis

DevFeed: [EDA: Observe, Verify, and Assess for Evidence-Grounded Multimodal Depression Analysis](<https://devfeed.tech/articles/eda-observe-verify-and-assess-for-evidence-grounded-multimodal-depression-analysis-140061.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.22648>)

Author: Changzeng Fu, Ming Shang, Xinyi Zhang, Jiadong Wang, Runhao Zeng, Shiqi Zhao

Published: 2026-11-18T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [AI Chat](<https://devfeed.tech/topics/ai-chat.md>), [Data analysis](<https://devfeed.tech/topics/data-analysis.md>), [human review](<https://devfeed.tech/topics/human-review.md>), [Natural language processing](<https://devfeed.tech/topics/nlp.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [depression](<https://devfeed.tech/tags/depression.md>), [eda](<https://devfeed.tech/tags/eda.md>), [grounded](<https://devfeed.tech/tags/grounded.md>), [multimodal](<https://devfeed.tech/tags/multimodal.md>), [verify](<https://devfeed.tech/tags/verify.md>)

### AI overview

EDA makes multimodal depression assessment more inspectable by linking behavioral observations to specific media segments and measurements. Its Observe stage localizes literature-informed acoustic and visual cues; Verify uses frozen multimodal agents to check whether cited media support them, with the Support policy admitting positively verified records and review grounds. Assess compares behavior using statistical descriptors and temporal events, adds PHQ-9-guided text analysis, and reviews original text when modalities disagree. On shared source segments, AI cue annotations reached 91.02% accuracy against human consensus. With a frozen 7B backbone, EDA Support improved F1 over direct prediction by 7.61 percentage points on D-Vlog Leave-Query-Out and 9.88 points on LMVD. The excerpt reports cue agreement and downstream utility separately.

### Source excerpt

arXiv:2611.22648v1 Announce Type: new Abstract: Existing multimodal depression assessment methods often summarize long recordings into global behavioral descriptions. This leaves the source and decision relevance of individual observations difficult to inspect. We propose EDA, an evidence-grounded framework organized around Observe, Verify, and Assess. In Observe, literature-informed acoustic and visual cues are localized into source-linked Evidence Records with temporal intervals and behavioral measurements. In Verify, frozen multimodal agents examine whether the cited media support each observation. The simplified Support admission policy retains positively verified records and their review grounds. In Assess, statistical descriptors and temporal events support reference-based behavioral comparison, while PHQ-9-guided text analysis provides complementary symptom evidence. Cross-modal disagreement triggers review of the original text before final selection. Experiments on D-Vlog and LMVD evaluate human-referenced cue agreement and downstream assessment utility separately. AI cue annotations achieve 91.02% accuracy against human consensus labels on shared source segments. With a frozen 7B backbone, EDA Support improves F1 over direct prediction by 7.61 and 9.88 percentage points on D-Vlog Leave-Query-Out and LMVD, respectively. These findings support explicit, source-linked behavioral evidence for inspectable multimodal depression assessment.

## Benchmarked: A data pipeline latency analysis

DevFeed: [Benchmarked: A data pipeline latency analysis](<https://devfeed.tech/articles/benchmarked-a-data-pipeline-latency-analysis-140198.md>)

Original publisher: [Read original article](<https://wf.fivetran.com/blog/benchmarked-a-data-pipeline-latency-analysis>)

Author: Eric O'Connor

Published: 2026-11-18T04:00:45Z

Content type: article

Language: en

Sources: [Fivetran Blog](<https://devfeed.tech/sources/fivetran-blog.md>)

Topics: [Data pipelines](<https://devfeed.tech/topics/data-pipelines.md>), [performance-engineering](<https://devfeed.tech/topics/performance-engineering.md>), [Data analysis](<https://devfeed.tech/topics/data-analysis.md>), [data transformation](<https://devfeed.tech/topics/data-transformation.md>)

Tags: [analysis](<https://devfeed.tech/tags/analysis.md>), [change-data-capture](<https://devfeed.tech/tags/change-data-capture.md>), [data](<https://devfeed.tech/tags/data.md>), [data-pipeline](<https://devfeed.tech/tags/data-pipeline.md>), [data-pipeline-performance](<https://devfeed.tech/tags/data-pipeline-performance.md>), [fivetran](<https://devfeed.tech/tags/fivetran.md>), [latency](<https://devfeed.tech/tags/latency.md>)

### AI overview

Fivetran's incremental-sync benchmark reports that, in most cases, it delivered data to Snowflake in under 17 minutes while handling a simulated workload of about 240 GB per hour and roughly 16,000 transactions per second on a single-node database. The test used HammerDB's TPROC-C workload, augmented with detail columns to bring average row width to about 1 KB, and measured freshness from gaps between periodic micro-batch syncs. Latency depends on workload size; the authors expect less intensive workloads to support lower latency. The excerpt describes Oracle-to-Snowflake results and says the framework was being extended to other configurations.

### Source excerpt

Learn how Fivetran measures the latency of our pipelines.

## Get Started With the "T" in ELT | Blog | Fivetran

DevFeed: [Get Started With the "T" in ELT | Blog | Fivetran](<https://devfeed.tech/articles/get-started-with-the-t-in-elt-blog-fivetran-140259.md>)

Original publisher: [Read original article](<https://wf.fivetran.com/blog/start-with-t-elt>)

Author: Charles Wang

Published: 2026-11-18T03:38:23Z

Content type: tutorial

Language: en

Sources: [Fivetran Blog](<https://devfeed.tech/sources/fivetran-blog.md>)

Topics: [elt](<https://devfeed.tech/topics/elt.md>), [data-engineering](<https://devfeed.tech/topics/data-engineering.md>), [Data analysis](<https://devfeed.tech/topics/data-analysis.md>)

Tags: [aggregate](<https://devfeed.tech/tags/aggregate.md>), [aggregate-functions](<https://devfeed.tech/tags/aggregate-functions.md>), [analysis](<https://devfeed.tech/tags/analysis.md>), [arithmetic](<https://devfeed.tech/tags/arithmetic.md>), [bigquery](<https://devfeed.tech/tags/bigquery.md>), [computing](<https://devfeed.tech/tags/computing.md>), [conversion](<https://devfeed.tech/tags/conversion.md>), [cost](<https://devfeed.tech/tags/cost.md>), [data](<https://devfeed.tech/tags/data.md>), [data-analysis](<https://devfeed.tech/tags/data-analysis.md>), [data-validation](<https://devfeed.tech/tags/data-validation.md>), [data-warehouse](<https://devfeed.tech/tags/data-warehouse.md>), [deduplication](<https://devfeed.tech/tags/deduplication.md>), [elt](<https://devfeed.tech/tags/elt.md>), [fivetran](<https://devfeed.tech/tags/fivetran.md>), [formatting](<https://devfeed.tech/tags/formatting.md>), [functions](<https://devfeed.tech/tags/functions.md>), [id](<https://devfeed.tech/tags/id.md>), [identifier](<https://devfeed.tech/tags/identifier.md>), [reporting](<https://devfeed.tech/tags/reporting.md>)

### AI overview

Fivetran Transformations applies scheduled, materialized SQL transformations that create or replace warehouse tables; each script names its destination schema and table. The article contrasts these stored results with views, which run queries on access and may perform poorly on large tables or complex queries. It groups transformations into revising data (cleaning, conversion, deduplication and validation), computing values (calculations, summaries and pivots), separating data (splitting and filtering), and combining sources (joins, unions and integration). Examples cover normalizing text and units, creating participant identifiers after excluding missing emails, calculating BMI and summary statistics, joining percentile results, pivoting enumerated activity values, and splitting comma-separated nicknames. The article says the nickname example works only in Snowflake at the time of writing; when a platform lacks PIVOT, it shows conditional aggregation as an alternative.

### Source excerpt

Use Fivetran Transformations to prepare your data for reporting.

## 2021 BI Trends and Predictions | Blog | Fivetran

DevFeed: [2021 BI Trends and Predictions | Blog | Fivetran](<https://devfeed.tech/articles/2021-bi-trends-and-predictions-blog-fivetran-140185.md>)

Original publisher: [Read original article](<https://wf.fivetran.com/blog/2021-bi-trends-predictions>)

Author: Cat Origitano

Published: 2026-11-18T03:38:23Z

Content type: article

Language: en

Sources: [Fivetran Blog](<https://devfeed.tech/sources/fivetran-blog.md>)

Topics: [Data analysis](<https://devfeed.tech/topics/data-analysis.md>), [dashboards](<https://devfeed.tech/topics/dashboards.md>), [Data pipelines](<https://devfeed.tech/topics/data-pipelines.md>), [AI-Ready Data](<https://devfeed.tech/topics/ai-ready-data.md>)

Tags: [2](<https://devfeed.tech/tags/2.md>), [2020](<https://devfeed.tech/tags/2020.md>), [2021](<https://devfeed.tech/tags/2021.md>), [about](<https://devfeed.tech/tags/about.md>), [accessible](<https://devfeed.tech/tags/accessible.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-artificial-intelligence](<https://devfeed.tech/tags/ai-artificial-intelligence.md>), [all](<https://devfeed.tech/tags/all.md>), [allows](<https://devfeed.tech/tags/allows.md>), [also](<https://devfeed.tech/tags/also.md>), [bi](<https://devfeed.tech/tags/bi.md>), [blog](<https://devfeed.tech/tags/blog.md>), [crystal](<https://devfeed.tech/tags/crystal.md>), [dashboard](<https://devfeed.tech/tags/dashboard.md>), [data](<https://devfeed.tech/tags/data.md>), [death](<https://devfeed.tech/tags/death.md>), [fivetran](<https://devfeed.tech/tags/fivetran.md>), [predictions](<https://devfeed.tech/tags/predictions.md>), [rise](<https://devfeed.tech/tags/rise.md>), [trends](<https://devfeed.tech/tags/trends.md>)

### AI overview

The excerpt predicts that BI in 2021 will move from static dashboards and siloed analysis toward flexible, near real-time exploration and collaborative work. It argues that timely, accessible data supports decisions, but meaningful interpretation still depends on business context and human experience that AI cannot supply. On governance, it favors a balance between unrestricted access and control so data remains usable. It also points to capturing contextual information from documents and spreadsheets alongside platform data. The article leaves some implementation details--especially for governance and self-service BI--to the full ebook.

### Source excerpt

From the rise of real data to the death of the dashboard, we pull out our crystal ball and predict the most impactful BI trends for 2021.

## Funnel Analysis and Conversion Metrics in SQL | Blog | Fivetran

DevFeed: [Funnel Analysis and Conversion Metrics in SQL | Blog | Fivetran](<https://devfeed.tech/articles/funnel-analysis-and-conversion-metrics-in-sql-blog-fivetran-140233.md>)

Original publisher: [Read original article](<https://wf.fivetran.com/blog/funnel-analysis>)

Author: Charles Wang

Published: 2026-11-18T03:38:23Z

Content type: tutorial

Language: en

Sources: [Fivetran Blog](<https://devfeed.tech/sources/fivetran-blog.md>)

Topics: [SQL](<https://devfeed.tech/topics/sql.md>), [Data analysis](<https://devfeed.tech/topics/data-analysis.md>), [Query (disambiguation)](<https://devfeed.tech/topics/query.md>)

Tags: [aggregation](<https://devfeed.tech/tags/aggregation.md>), [analysis](<https://devfeed.tech/tags/analysis.md>), [business](<https://devfeed.tech/tags/business.md>), [business-operations](<https://devfeed.tech/tags/business-operations.md>), [client](<https://devfeed.tech/tags/client.md>), [clients](<https://devfeed.tech/tags/clients.md>), [connectors](<https://devfeed.tech/tags/connectors.md>), [conversion](<https://devfeed.tech/tags/conversion.md>), [count](<https://devfeed.tech/tags/count.md>), [customer](<https://devfeed.tech/tags/customer.md>), [customer-success](<https://devfeed.tech/tags/customer-success.md>), [data](<https://devfeed.tech/tags/data.md>), [event](<https://devfeed.tech/tags/event.md>), [events](<https://devfeed.tech/tags/events.md>), [fivetran](<https://devfeed.tech/tags/fivetran.md>), [function](<https://devfeed.tech/tags/function.md>), [funnel](<https://devfeed.tech/tags/funnel.md>), [funnel-analysis](<https://devfeed.tech/tags/funnel-analysis.md>), [metrics](<https://devfeed.tech/tags/metrics.md>), [sql](<https://devfeed.tech/tags/sql.md>)

### AI overview

The article shows how to measure a sales funnel from event counts in SQL. Starting with grouped counts by event, it derives each stage's share of the largest count and uses the LAG window function to compare each stage with the preceding one, yielding a step-to-step survival rate. In the mock 2018 cohort, negotiation-to-registration is the largest proportional choke point at about 38%, suggesting negotiation tactics as a possible focus for intervention. Funnel stages vary by process; the example notes that Salesforce opportunity history may use stages such as contacted, qualified, and won. Cohort analysis is outside the excerpt's scope.

### Source excerpt

Using SQL to conduct funnel analysis can help you make sense of multiple facets of your business.

## In uncertain markets, businesses invest in data | Blog | Fivetran

DevFeed: [In uncertain markets, businesses invest in data | Blog | Fivetran](<https://devfeed.tech/articles/in-uncertain-markets-businesses-invest-in-data-blog-fivetran-140240.md>)

Original publisher: [Read original article](<https://wf.fivetran.com/blog/in-uncertain-markets-businesses-invest-in-data>)

Author: Fivetran

Published: 2026-11-18T03:07:10Z

Content type: article

Language: en

Sources: [Fivetran Blog](<https://devfeed.tech/sources/fivetran-blog.md>)

Topics: [analytics stack](<https://devfeed.tech/topics/analytics-stack.md>), [data-engineering](<https://devfeed.tech/topics/data-engineering.md>), [Data analysis](<https://devfeed.tech/topics/data-analysis.md>), [Data pipelines](<https://devfeed.tech/topics/data-pipelines.md>), [data](<https://devfeed.tech/topics/data.md>), [elt](<https://devfeed.tech/topics/elt.md>), [etl](<https://devfeed.tech/topics/etl.md>)

Tags: [agile](<https://devfeed.tech/tags/agile.md>), [andreessen-horowitz](<https://devfeed.tech/tags/andreessen-horowitz.md>), [aws](<https://devfeed.tech/tags/aws.md>), [business-operations](<https://devfeed.tech/tags/business-operations.md>), [c-suite](<https://devfeed.tech/tags/c-suite.md>), [career](<https://devfeed.tech/tags/career.md>), [cio](<https://devfeed.tech/tags/cio.md>), [cios](<https://devfeed.tech/tags/cios.md>), [cloud](<https://devfeed.tech/tags/cloud.md>), [cloud-data](<https://devfeed.tech/tags/cloud-data.md>), [construction](<https://devfeed.tech/tags/construction.md>), [customer](<https://devfeed.tech/tags/customer.md>), [customer-experience](<https://devfeed.tech/tags/customer-experience.md>), [customers](<https://devfeed.tech/tags/customers.md>), [data](<https://devfeed.tech/tags/data.md>), [data-stack](<https://devfeed.tech/tags/data-stack.md>), [fivetran](<https://devfeed.tech/tags/fivetran.md>), [invest](<https://devfeed.tech/tags/invest.md>), [markets](<https://devfeed.tech/tags/markets.md>), [modern-data-stack](<https://devfeed.tech/tags/modern-data-stack.md>)

### AI overview

The article argues that accurate, current data consolidated for holistic analysis can help businesses respond to volatile markets by improving efficiency, identifying growth opportunities and speeding decisions across an organization. It describes Schüttflix centralizing customer, supplier and partner data to improve supply chain coverage and efficiency; 1-800-Flowers combining internal and purchased data to personalize customer experiences and find cross-sell and upsell opportunities; and a sportswear brand joining apparel and fitness-app data to build customer profiles. A logistics customer used broad, rapid data access to involve more employees in decisions. These are company-reported examples; the excerpt does not quantify results or compare data platforms.

### Source excerpt

Fivetran and our modern data stack partners are poised to thrive.

## To Become Data-Driven, Align Talent, Tools and Processes | Blog | Fivetran

DevFeed: [To Become Data-Driven, Align Talent, Tools and Processes | Blog | Fivetran](<https://devfeed.tech/articles/to-become-data-driven-align-talent-tools-and-processes-blog-fivetran-140262.md>)

Original publisher: [Read original article](<https://wf.fivetran.com/blog/to-become-data-driven-align-talent-tools-and-processes>)

Author: Adrian McGill

Published: 2026-11-18T02:45:59Z

Content type: article

Language: en

Sources: [Fivetran Blog](<https://devfeed.tech/sources/fivetran-blog.md>)

Topics: [Data analysis](<https://devfeed.tech/topics/data-analysis.md>), [business-intelligence](<https://devfeed.tech/topics/business-intelligence.md>), [decision-making](<https://devfeed.tech/topics/decision-making.md>), [data-engineering](<https://devfeed.tech/topics/data-engineering.md>)

Tags: [align](<https://devfeed.tech/tags/align.md>), [automate](<https://devfeed.tech/tags/automate.md>), [automated](<https://devfeed.tech/tags/automated.md>), [bi](<https://devfeed.tech/tags/bi.md>), [bi-tools](<https://devfeed.tech/tags/bi-tools.md>), [blog](<https://devfeed.tech/tags/blog.md>), [braze](<https://devfeed.tech/tags/braze.md>), [business](<https://devfeed.tech/tags/business.md>), [data](<https://devfeed.tech/tags/data.md>), [data-driven](<https://devfeed.tech/tags/data-driven.md>), [decision](<https://devfeed.tech/tags/decision.md>), [decision-making](<https://devfeed.tech/tags/decision-making.md>), [fivetran](<https://devfeed.tech/tags/fivetran.md>), [insights](<https://devfeed.tech/tags/insights.md>), [key](<https://devfeed.tech/tags/key.md>), [processes](<https://devfeed.tech/tags/processes.md>), [resources](<https://devfeed.tech/tags/resources.md>), [strategies](<https://devfeed.tech/tags/strategies.md>), [talent](<https://devfeed.tech/tags/talent.md>), [tools](<https://devfeed.tech/tags/tools.md>)

### AI overview

The article argues that becoming data-driven requires sustained alignment of people, processes, and technology--not just executive support or new tools. It recommends automating integration so analysts can focus on insights; partnering with an influential business stakeholder on a measurable revenue or cost proof of concept who can evangelize data use; presenting clear visual insights that guide action; giving business users one shareable BI tool as a single source of truth; and scaling adoption through business-led training in data analysis, interrogation, and visualization. The excerpt offers these as strategies, without evaluating particular BI tools.

### Source excerpt

Use these five strategies to align key resources and ensure that insights guide your decision-making.

## Don't let uncertainty cloud your vision - data clears the way | Blog | Fivetran

DevFeed: [Don't let uncertainty cloud your vision - data clears the way | Blog | Fivetran](<https://devfeed.tech/articles/don-t-let-uncertainty-cloud-your-vision-data-clears-the-way-blog-fivetran-140210.md>)

Original publisher: [Read original article](<https://wf.fivetran.com/blog/data-uncertain-times>)

Author: Fivetran

Published: 2026-11-18T02:45:50Z

Content type: article

Language: en

Sources: [Fivetran Blog](<https://devfeed.tech/sources/fivetran-blog.md>)

Topics: [Data analysis](<https://devfeed.tech/topics/data-analysis.md>), [BigQuery](<https://devfeed.tech/topics/bigquery.md>), [data analyst](<https://devfeed.tech/topics/data-analyst.md>)

Tags: [analysis](<https://devfeed.tech/tags/analysis.md>), [analyst](<https://devfeed.tech/tags/analyst.md>), [analytics](<https://devfeed.tech/tags/analytics.md>), [bigquery](<https://devfeed.tech/tags/bigquery.md>), [blog](<https://devfeed.tech/tags/blog.md>), [business](<https://devfeed.tech/tags/business.md>), [correlation](<https://devfeed.tech/tags/correlation.md>), [created](<https://devfeed.tech/tags/created.md>), [data](<https://devfeed.tech/tags/data.md>), [data-analysis](<https://devfeed.tech/tags/data-analysis.md>), [data-driven](<https://devfeed.tech/tags/data-driven.md>), [data-stack](<https://devfeed.tech/tags/data-stack.md>), [database](<https://devfeed.tech/tags/database.md>), [delta](<https://devfeed.tech/tags/delta.md>), [fivetran](<https://devfeed.tech/tags/fivetran.md>), [gap](<https://devfeed.tech/tags/gap.md>), [go-to-market](<https://devfeed.tech/tags/go-to-market.md>), [gtm](<https://devfeed.tech/tags/gtm.md>), [sales](<https://devfeed.tech/tags/sales.md>), [uncertainty](<https://devfeed.tech/tags/uncertainty.md>)

### AI overview

A comparison of production Postgres account creation data with Salesforce showed Salesforce recorded only about half the monthly accounts. Investigation found duplicates, partner and test accounts, but also real customers starting trials and connecting data without sales notification. In March, the team identified many such trials and shared the potential revenue gap with go-to-market partners; Fivetran says it is changing processes to address missed sales follow-up. The investigation used Postgres, Salesforce, Fivetran, BigQuery and Looker. The text describes a potential revenue opportunity, not a quantified realized loss or recovered revenue.

### Source excerpt

How we uncovered an unexpected sales opportunity through data sleuthing.

## Quantifying Membership Inference Risks in Genomic Data Sharing: The Role of Attacker's Auxiliary Information

DevFeed: [Quantifying Membership Inference Risks in Genomic Data Sharing: The Role of Attacker's Auxiliary Information](<https://devfeed.tech/articles/quantifying-membership-inference-risks-in-genomic-data-sharing-the-role-of-attacker-s-auxiliary-information-138801.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.18909>)

Author: Maryam Ghasemian, Lynette Hammond Gerido, Erman Ayday

Published: 2026-11-17T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Cryptography and Security](<https://devfeed.tech/sources/arxiv-cryptography-and-security.md>), [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Differential Privacy](<https://devfeed.tech/topics/differential-privacy.md>), [Security & Privacy](<https://devfeed.tech/topics/security-privacy.md>), [sensitive data](<https://devfeed.tech/topics/sensitive-data.md>), [Data analysis](<https://devfeed.tech/topics/data-analysis.md>)

Tags: [attack](<https://devfeed.tech/tags/attack.md>), [auditing](<https://devfeed.tech/tags/auditing.md>), [cs-cr](<https://devfeed.tech/tags/cs-cr.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [dataset](<https://devfeed.tech/tags/dataset.md>), [datasets](<https://devfeed.tech/tags/datasets.md>), [differential-privacy](<https://devfeed.tech/tags/differential-privacy.md>), [false-positive-rate](<https://devfeed.tech/tags/false-positive-rate.md>), [framework](<https://devfeed.tech/tags/framework.md>), [genomic-data](<https://devfeed.tech/tags/genomic-data.md>), [local](<https://devfeed.tech/tags/local.md>), [mechanism](<https://devfeed.tech/tags/mechanism.md>), [power](<https://devfeed.tech/tags/power.md>), [pre-release](<https://devfeed.tech/tags/pre-release.md>), [precision](<https://devfeed.tech/tags/precision.md>), [principal-component-analysis](<https://devfeed.tech/tags/principal-component-analysis.md>), [privacy](<https://devfeed.tech/tags/privacy.md>), [project](<https://devfeed.tech/tags/project.md>), [public](<https://devfeed.tech/tags/public.md>), [recall](<https://devfeed.tech/tags/recall.md>), [research](<https://devfeed.tech/tags/research.md>), [sharing](<https://devfeed.tech/tags/sharing.md>)

### AI overview

The proposed framework audits genomic datasets for membership inference risk before publication. It maps data into a shared PCA space, applies epsilon-local differential privacy with Laplace noise using a derived sensitivity for PCA scores, and measures a distance-threshold attack at a 5% false-positive rate. It also reports precision, recall, and an Unbiased Reconstruction Robustness membership-neutrality diagnostic. Experiments on openSNP and 1000 Genomes Project data across dimensionalities and privacy budgets identify separation between the research dataset and public auxiliary data in PCA space as a stronger determinant of attack success than perturbation level alone. A GWAS-style likelihood ratio test provides a comparison baseline.

### Source excerpt

arXiv:2611.18909v1 Announce Type: cross Abstract: Genomic data sharing is essential for biomedical research but introduces significant privacy risks, including membership inference attacks, in which an adversary determines whether a specific individual's data was used in a study. Existing privacy protections are typically applied after a release format has already been chosen, leaving researchers without a principled method to assess dataset-specific risk beforehand. We propose a server-assisted, principal component analysis-based pre-release auditing framework that maps genomic data into a shared low-dimensional space, applies epsilon-local differential privacy via the Laplace mechanism with a formally derived sensitivity for principal component analysis scores, and estimates membership inference attack power at a controlled 5% false-positive rate using a distance-threshold attack. A membership-neutrality diagnostic based on Unbiased Reconstruction Robustness is reported alongside attack power, precision, and recall. Experiments using the openSNP and 1000 Genomes Project datasets across multiple dimensionalities and privacy budgets show that separation between the researcher's dataset and public auxiliary data in principal component analysis space is a dominant determinant of attack success, exceeding the effect of perturbation level alone. Comparison against a genome-wide association study-style likelihood ratio test baseline further contextualizes the measured risk. This framework enables researchers, data repositories, and institutional review bodies to quantify dataset-specific membership inference risk before genomic data publication, supporting more informed and privacy-aware biomedical data-sharing decisions.

## UrbanROI: Causal Modeling for Regional ROI Forecasting under POI Entry

DevFeed: [UrbanROI: Causal Modeling for Regional ROI Forecasting under POI Entry](<https://devfeed.tech/articles/urbanroi-causal-modeling-for-regional-roi-forecasting-under-poi-entry-139004.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.20180>)

Author: Zhaoqi Zhang, Miao Xie, Linyou Cai, Qianlong Xie, Xingxing Wang, Siqiang Luo, Gao Cong

Published: 2026-11-17T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [causality](<https://devfeed.tech/topics/causality.md>), [Data analysis](<https://devfeed.tech/topics/data-analysis.md>)

Tags: [abstract](<https://devfeed.tech/tags/abstract.md>), [ads](<https://devfeed.tech/tags/ads.md>), [advertising](<https://devfeed.tech/tags/advertising.md>), [analysis](<https://devfeed.tech/tags/analysis.md>), [business](<https://devfeed.tech/tags/business.md>), [competition](<https://devfeed.tech/tags/competition.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [datasets](<https://devfeed.tech/tags/datasets.md>), [decision](<https://devfeed.tech/tags/decision.md>), [decision-making](<https://devfeed.tech/tags/decision-making.md>), [effects](<https://devfeed.tech/tags/effects.md>), [evolution](<https://devfeed.tech/tags/evolution.md>), [forecasting](<https://devfeed.tech/tags/forecasting.md>), [framework](<https://devfeed.tech/tags/framework.md>), [future](<https://devfeed.tech/tags/future.md>), [graph](<https://devfeed.tech/tags/graph.md>), [graphs](<https://devfeed.tech/tags/graphs.md>), [impact](<https://devfeed.tech/tags/impact.md>), [interaction](<https://devfeed.tech/tags/interaction.md>), [modeling](<https://devfeed.tech/tags/modeling.md>), [roi](<https://devfeed.tech/tags/roi.md>)

### AI overview

UrbanROI forecasts how a commercial region's ROI trajectory may change after a new point of interest (POI) enters. It addresses a gap in methods focused on individual ads or merchants by modeling temporal ROI and competition among surrounding POIs. Its Interaction-aware Regional Graph Module uses user request contexts, spatial proximity, and request-level commercial signals to represent competitive relationships; structurally aligned treatment and control graphs simulate factual and counterfactual regional states. The abstract reports that experiments on large-scale real-world POI and advertising datasets found UrbanROI consistently outperformed strong baselines in post-entry regional ROI forecasting.

### Source excerpt

arXiv:2611.20180v1 Announce Type: new Abstract: As urban commercial environments continue to evolve rapidly, accurately modeling the economic impact of point of interest (POI) entry is essential for supporting data-driven advertising allocation, merchant onboarding, and regional business decision-making. Existing return on investment (ROI) prediction methods mainly focus on individual ads or merchants, overlooking the interaction effects among POIs and failing to capture the causal influence of structural changes in urban commercial ecosystems. In this paper, we introduce a novel research problem -- regional ROI forecasting under POI entry, which aims to predict the future ROI trajectory of a commercial region after the introduction of a new POI by modeling temporal ROI evolution and competition-driven interactions among surrounding POIs. To address these challenges, we propose UrbanROI, an intervention-aware causal forecasting framework for region-level economic outcome prediction. UrbanROI leverages an Interaction-aware Regional Graph Module to explicitly model competitive relationships among POIs based on user request contexts, spatial proximity, and request-level commercial signals, and constructs structurally aligned treatment and control graphs to simulate factual and counterfactual regional states. Extensive experiments on large-scale real-world POI and advertising datasets demonstrate that UrbanROI consistently outperforms strong baselines in post-entry regional ROI forecasting. The results demonstrate its effectiveness in temporal economic modeling, inter-POI interaction representation, and intervention-aware forecasting, providing support for regional economic analysis and business decision-making in dynamic urban commercial systems.

[Next page](<https://devfeed.tech/topics/data-analysis.md?cursor=WyIyMDI2LTExLTE3VDA1OjAwOjAwKzAwOjAwIiwgImNmMGQ4MzdlLTMxOWItNGVkOS04ZGY2LWIxMzlhNTNmOTViNSJd>)