# forecasting Published articles for forecasting. This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles. ## Multi-modal autoscaling with Amazon EC2 Auto Scaling: adding signals for faster, more reliable scaling DevFeed: [Multi-modal autoscaling with Amazon EC2 Auto Scaling: adding signals for faster, more reliable scaling]() Original publisher: [Read original article]() Author: Shubhendu Dubey Published: 2026-09-17T18:18:38Z Content type: tutorial Language: en Sources: [AWS Compute Blog]() Topics: [autoscaling](), [Amazon EC2](), [scaling](), [Amazon CloudWatch](), [Amazon Web Services](), [AWS CloudFormation](), [Deployment](), [dashboards]() Tags: [advanced-300](), [amazon-cloudwatch](), [amazon-ec2](), [api](), [auto-scaling](), [autoscaling](), [aws](), [aws-cloudformation](), [deployment](), [forecasting](), [latency](), [load](), [load-balancer](), [scaling](), [technical-how-to]() ### AI overview This tutorial explains multi-modal autoscaling with Amazon EC2 Auto Scaling by combining CPU, request-count, application-level, and predictive signals. It describes a controlled test in which application metrics avoided rejected checkout sessions and reduced p99 latency compared with CPU-only scaling. ### Source excerpt Multi-modal autoscaling with Amazon EC2 Auto Scaling combines infrastructure metrics like CPU with application-level signals, so a group scales on the demand its users create. In this post, we show you how to implement it, with code samples and results from a controlled test. ## Forking-Sequences -- Part II: Multi-Horizon Forecast Ensembling with Reduced Volatility DevFeed: [Forking-Sequences -- Part II: Multi-Horizon Forecast Ensembling with Reduced Volatility]() Original publisher: [Read original article]() Author: Willa Potosnak Published: 2026-08-10T21:52:23Z Content type: article Language: en Sources: [ML@CMU]() Topics: [Sequences](), [Time Series](), [foundation-models](), [Inference](), [Machine Learning & Artificial Intelligence]() Tags: [ai](), [artificial-intelligence](), [automated-machine-learning](), [big-data](), [computer-science](), [data-science](), [deep-learning](), [ethics-and-ai](), [forecasting](), [foundation-models](), [inference](), [machine-learning](), [ml](), [multi-horizon-forecasting](), [natural-language-processing](), [neural-networks](), [paper](), [research](), [sequences](), [time-series]() ### AI overview The article describes forecast ensembling for multi-horizon time-series models. Exponential smoothing reduces forecast volatility by about 10-13% with less than 0.1% accuracy degradation, including in zero-shot use with pretrained time-series foundation models. ### Source excerpt Based on: Potosnak, W., Wolff, M., Cao, M., Ma, R., Konstantinova, T., Efimov, D., Mahoney, M.W., Oreshkin, B., & Olivares, K.G. "Forking-Sequences: Statistically and Computationally Efficient Multi-Horizon Forecasting with Reduced Volatility." Transactions on Machine Learning Research, 2026. (Disclaimer: Code implementation not used in the paper; not affiliated with Amazon -- provided as a reference for forking-sequences and forecast ensembling) TL;DR Ensembling, nearly for free. Forking-sequences already produces overlapping forecasts for every target date across FCDs in a single forward pass, so ensembling them at inference adds no extra encoder computation compared with window-sampling. Two new forecast volatility metrics. scaled Forecast Percentage Change (sFPC) measures raw revision size in real time (no ground truth needed); Excess Volatility (EV) goes further, rewarding accuracy-improving revisions and only penalizing the ones that move forecasts away from the truth or overshoot it. Reduced volatility without sacrificing accuracy. Exponential-smoothing forecast ensembling (α = 0.9) reduces sEV by 10-13% across all encoder types, with less than 0.1% accuracy degradation. Works zero-shot on models pretrained with window-sampling. Forecast ensembling applied to pretrained Time Series Foundation Models (TSFMs) -- Chronos-2, Toto 2.0, TimesFM, PatchTST, N-BEATS -- cuts volatility by ~10% with negligible accuracy cost (less than 0.1%). In Part [...] ## Proactive FinOps Strategies for Optimizing Cloud Savings DevFeed: [Proactive FinOps Strategies for Optimizing Cloud Savings]() Original publisher: [Read original article]() Author: Kelsey Rosen Published: 2026-08-10T00:00:00Z Content type: article Language: en Sources: [Harness Blog]() Topics: [finops](), [cloud cost management](), [Optimization](), [Cloud](), [Automation]() Tags: [automation](), [cloud](), [cloud-cost-management](), [cost-optimization](), [finops](), [forecasting](), [governance](), [optimization]() ### AI overview The article argues that FinOps teams should move beyond reactive overspend reduction toward proactive savings optimization. It describes continuous visibility, automated governance, forecasting, and ongoing optimization as ways to identify missed cloud savings before inefficiency compounds. ### Source excerpt Shift your FinOps paradigm from overspending to under-saving. Discover proactive cloud cost optimization strategies. Learn more with Harness CCM. | Blog ## Devavrat Shah's research and Ikigai Labs use tabular data for real-time forecasting and decision-making DevFeed: [Devavrat Shah's research and Ikigai Labs use tabular data for real-time forecasting and decision-making]() Original publisher: [Read original article]() Author: David Chandler | Laboratory for Information and Decision Systems Published: 2026-07-14T20:25:00Z Content type: article Language: en Sources: [MIT AI News]() Topics: [Artificial Intelligence](), [decision-making](), [Structured-data](), [AI Models](), [data](), [Time Series](), [Computer science](), [Electrical engineering and computer science (EECS)](), [Temporal data](), [systems]() Tags: [ai](), [ai-and-decision-making](), [ai-in-business-planning](), [ai-models](), [algorithms](), [artificial-intelligence](), [business-and-management](), [business-modeling](), [celonis-context-model](), [computer-science-and-technology](), [data](), [data-systems](), [decision-making](), [devavrat-shah](), [electrical-engineering-and-computer-science-eecs](), [faculty](), [forecasting](), [idss](), [ikigailabs](), [laboratory-for-information-and-decision-systems-lids](), [mit-eecs](), [mit-idss](), [mit-intellectual-property](), [mit-lids](), [mit-schwarzman-college-of-computing](), [predictions](), [profile](), [real-time](), [research](), [school-of-engineering](), [startups](), [structured](), [tabular-data](), [time-series-data]() ### AI overview MIT Professor Devavrat Shah's research led to a foundation model for tabular and time-series enterprise data. Developed with Ikigai Labs, the system continuously tests predictions against real outcomes to support large-scale forecasting and decision-making. ### Source excerpt Through research and entrepreneurship, Professor Devavrat Shah is helping to design methods that can handle constant decision-making using limited computational resources. ## Revenue Forecasting for SaaS: Models and Methods DevFeed: [Revenue Forecasting for SaaS: Models and Methods]() Original publisher: [Read original article]() Author: Ayush Agarwal Published: 2026-04-12T00:00:00Z Content type: tutorial Language: en Sources: [Dodo Payments Blog]() Topics: [Software as a service](), [Finance]() Tags: [accounting](), [business](), [forecasting](), [future](), [guide](), [how-to](), [implementation](), [learn](), [metric](), [metrics](), [models](), [pipeline](), [revenue](), [saas](), [saas-finance](), [saas-metrics]() ### AI overview A practical guide to SaaS revenue forecasting that explains forecasting models, MRR and ARR logic, cohort behavior, pipeline assumptions, and scenario planning. It also discusses how billing details such as churn, expansion, contractions, annual prepayments, and recognized revenue affect forecast accuracy. ### Source excerpt Learn how to build a SaaS revenue forecasting model using MRR movements, cohort behavior, pipeline assumptions, and scenario planning that finance teams can trust. ## SaaS Gross Margin: How to Calculate and What Good Looks Like DevFeed: [SaaS Gross Margin: How to Calculate and What Good Looks Like]() Original publisher: [Read original article]() Author: Ayush Agarwal Published: 2026-04-12T00:00:00Z Content type: tutorial Language: en Sources: [Dodo Payments Blog]() Topics: [Software as a service](), [Finance](), [Software]() Tags: [churn](), [cost](), [economics](), [finance](), [forecasting](), [growth](), [how-to](), [pricing](), [revenue](), [saas](), [saas-finance](), [subscriptions]() ### AI overview A practical guide to SaaS gross margin explains how to calculate the metric, which costs belong in cost of revenue, why margin affects growth and business quality, and how teams can improve it without damaging growth. ### Source excerpt Learn how to calculate SaaS gross margin, which costs belong in cost of revenue, and what margin ranges are healthy for different stages of a software business. ## What are billing credits? How billing credits improve cashflow and user experience DevFeed: [What are billing credits? How billing credits improve cashflow and user experience]() Original publisher: [Read original article]() Author: Joshua D'Costa Published: 2025-11-30T00:00:00Z Content type: tutorial Language: en Sources: [Dodo Payments Blog]() Topics: [Software as a service](), [User Experience](), [API]() Tags: [billing](), [customer-experience](), [customers](), [experience](), [forecasting](), [pricing](), [saas]() ### AI overview This tutorial explains billing credits as prepaid account value deducted as customers use a product. It covers prepaid, promotional, and refund-as-credit models, along with credit valuation, top-ups, expiration or rollover policies, ledger tracking, and customer-facing display. It describes how credits can support SaaS cash flow, spending visibility, forecasting, and customer experience. ### Source excerpt Learn what billing credits are, how credit-based pricing works, and how billing credits improve SaaS cash flow, forecasting, and customer experience. ## AutoBNN: Probabilistic time series forecasting with compositional bayesian neural networks DevFeed: [AutoBNN: Probabilistic time series forecasting with compositional bayesian neural networks]() Original publisher: [Read original article]() Author: Google AI (noreply@blogger.com) Published: 2024-03-28T20:53:00Z Content type: article Language: en Sources: [Google Research]() Topics: [Time Series](), [Google](), [Open Source]() Tags: [data](), [forecasting](), [google](), [kernels](), [machine-learning](), [model](), [neural-networks](), [open-source](), [patterns](), [research](), [statistics](), [time-series]() ### AI overview Google Research introduces AutoBNN, an open-source JAX package for automatically discovering interpretable probabilistic time series forecasting models. It combines learned compositional Gaussian process kernels with neural-network scalability and provides uncertainty estimates for large datasets. ### Source excerpt Posted by Urs Köster, Software Engineer, Google Research Time series problems are ubiquitous, from forecasting weather and traffic patterns to understanding economic trends. Bayesian approaches start with an assumption about the data's patterns (prior probability), collecting evidence (e.g., new time series data), and continuously updating that assumption to form a posterior probability distribution. Traditional Bayesian approaches like Gaussian processes (GPs) and Structural Time Series are extensively used for modeling time series data, e.g., the commonly used Mauna Loa CO2 dataset. However, they often rely on domain experts to painstakingly select appropriate model components and may be computationally expensive. Alternatives such as neural networks lack interpretability, making it difficult to understand how they generate forecasts, and don't produce reliable confidence intervals. To that end, we introduce AutoBNN, a new open-source package written in JAX. AutoBNN automates the discovery of interpretable time series forecasting models, provides high-quality uncertainty estimates, and scales effectively for use on large datasets. We describe how AutoBNN combines the interpretability of traditional probabilistic approaches with the scalability and flexibility of neural networks. AutoBNN AutoBNN is based on a line of research that over the past decade has yielded improved predictive accuracy by modeling time series using GPs with learned kernel structures. The kernel function of a GP encodes assumptions about the function being modeled, such as the presence of trends, periodicity or noise. With learned GP kernels, the kernel function is defined compositionally: it is either a base kernel (such as Linear, Quadratic, Periodic, Matérn or ExponentiatedQuadratic) or a composite that combines two or more kernel functions using operators such as Addition, Multiplication, or ChangePoint. This compositional kernel structure serves two related purposes. First, it is simple e ## A decoder-only foundation model for time-series forecasting DevFeed: [A decoder-only foundation model for time-series forecasting]() Original publisher: [Read original article]() Author: Google AI (noreply@blogger.com) Published: 2024-02-02T19:07:00Z Content type: article Language: en Sources: [Google Research]() Topics: [Time Series](), [foundation-models](), [Google](), [Deep learning]() Tags: [deep-learning](), [forecasting](), [google](), [google-cloud-platform](), [machine-learning](), [model](), [time-series]() ### AI overview Google Research introduces TimesFM, a decoder-only foundation model for time-series forecasting. The model is pretrained on 100 billion real-world time-points and is reported to provide zero-shot forecasts on unseen datasets across domains and temporal granularities, with 200 million parameters. ### Source excerpt Posted by Rajat Sen and Yichen Zhou, Google Research Time-series forecasting is ubiquitous in various domains, such as retail, finance, manufacturing, healthcare and natural sciences. In retail use cases, for example, it has been observed that improving demand forecasting accuracy can meaningfully reduce inventory costs and increase revenue. Deep learning (DL) models have emerged as a popular approach for forecasting rich, multivariate, time-series data because they have proven to perform well in a variety of settings (e.g., DL models performed well in the M5 competition). At the same time, there has been rapid progress in large foundation language models used for natural language processing (NLP) tasks, such as translation, retrieval-augmented generation, and code completion. These models are trained on massive amounts of textual data derived from a variety of sources like common crawl and open-source code that allows them to identify patterns in languages. This makes them very powerful zero-shot tools; for instance, when paired with retrieval, they can answer questions about and summarize current events. Despite DL-based forecasters largely outperforming traditional methods and progress being made in reducing training and inference costs, they face challenges: most DL architectures require long and involved training and validation cycles before a customer can test the model on a new time-series. A foundation model for time-series forecasting, in contrast, can provide decent out-of-the-box forecasts on unseen time-series data with no additional training, enabling users to focus on refining forecasts for the actual downstream task like retail demand planning. To that end, in "A decoder-only foundation model for time-series forecasting", we introduce TimesFM, a single forecasting model pre-trained on a large time-series corpus of 100 billion real world time-points. Compared to the latest large language models (LLMs), TimesFM is much smaller (200M parameters), yet we ## Visualizing information propagation in markets DevFeed: [Visualizing information propagation in markets]() Original publisher: [Read original article]() Author: Ricson Cheng Published: 2022-11-23T00:00:00Z Content type: article Language: en Sources: [Jane Street]() Topics: [Transactions](), [data]() Tags: [data](), [forecasting](), [future](), [hedge](), [index](), [information](), [transactions](), [uk](), [visualization]() ### AI overview The article uses the historical Dojima rice market and the story of Forecasting Yomiji to introduce how price information propagated through markets. It then presents a visualization of information transmission through fiber-optic cables using data from futures exchanges around the world, with equity index futures as an example. ### Source excerpt The Dojima rice market, established around 1716, is widely considered to be the world's first organized futures exchange. Instead of directly exchanging money for rice on the spot, merchants would agree on a price and future date at which rice and money would be exchanged. This allowed farmers and consumers to hedge their risk. As a result, information about the abundance or lack of rice would travel across the country as fast as rice merchants carried it. ## Load Testing APIs for Holiday Traffic and Dynamic Scalability DevFeed: [Load Testing APIs for Holiday Traffic and Dynamic Scalability]() Original publisher: [Read original article]() Published: 2018-12-31T17:00:00Z Content type: tutorial Language: en Sources: [Curalate]() Topics: [Testing](), [Scalability](), [Availability](), [Low Latency](), [Network](), [API](), [data](), [Bash]() Tags: [api](), [availability](), [bash](), [data](), [forecasting](), [holiday](), [infrastructure](), [load-testing](), [low-latency](), [network](), [scalability](), [testing]() ### AI overview This engineering article explains how Curalate prepared its APIs and infrastructure for increased holiday traffic. It describes using historical traffic data to estimate peak requests per second, load testing with steadily increasing request rates, and dynamic scalability to avoid over-provisioning costs. ### Source excerpt If you're a brick-and-mortar business owner, you quickly identify patterns in your customer foot traffic, especially around the holidays when achieving your sales goals depends on both timely and quality service. If you're an e-commerce business owner, like many of Curalate's 1,000+ customers, it's really no different: holiday sales are crucial to success and they depend heavily on your site's reliability. At Curalate, we take great pride in maintaining high availability and low latency for our client integrations throughout the year. But over the "Black Fiveday" period--Thanksgiving through Cyber Monday--and the week leading up to and including the day after Christmas, we see a roughly 5x increase in network requests to our APIs from our clients' sites. Therefore it's crucial that we both design our systems to handle that increased load and perform load testing on the systems ahead of time to prove that our designs work. This post describes how we carried out load tests of our infrastructure to prepare for the holiday traffic increase on our APIs. Additionally, it highlights how our approach towards dynamic scalability reduces costs by avoiding over-provisioning. Load Test Planning Our first question was: what volume of traffic can we expect? To answer that, we consulted the last several years of data describing our holiday traffic load pattern. Second: what are the important dimensions of that traffic? For example, do we expect a majority of the traffic to be cached or uncached? Do total requests matter or only instantaneous load? Since a previous blog post discussed cached versus uncached testing, this post focuses on API request rate. Total requests in a day is interesting, but only suggests an average requests-per-second (RPS) rate. The metric we're mostly interested in is the daily peak RPS rate. This gives us an idea of the busiest moment in our day, and if we can handle that rate, we should have confidence that we can handle lesser request rates at other times