# Zalando Science

Published articles for Zalando Science.

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

## Paper Announcement: A Practical Approach to Replenishment Optimization with Extended (R, s, Q) Policy and Probabilistic Models

DevFeed: [Paper Announcement: A Practical Approach to Replenishment Optimization with Extended (R, s, Q) Policy and Probabilistic Models](<https://devfeed.tech/articles/paper-announcement-a-practical-approach-to-replenishment-optimization-with-extended-r-s-q-policy-and-probabilistic-models-47498.md>)

Original publisher: [Read original article](<https://engineering.zalando.com/posts/2026/01/publication-replenishment-engine.html>)

Author: Alva Presbitero

Published: 2026-01-14T23:00:00Z

Content type: article

Language: en

Sources: [Zalando](<https://devfeed.tech/sources/zalando-engineering-blog.md>)

Topics: [Optimization](<https://devfeed.tech/topics/optimization.md>), [Simulation](<https://devfeed.tech/topics/simulation.md>), [data](<https://devfeed.tech/topics/data.md>), [Risk](<https://devfeed.tech/topics/risk.md>)

Tags: [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [backend](<https://devfeed.tech/tags/backend.md>), [data](<https://devfeed.tech/tags/data.md>), [demand-forecasting](<https://devfeed.tech/tags/demand-forecasting.md>), [logistics](<https://devfeed.tech/tags/logistics.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [models](<https://devfeed.tech/tags/models.md>), [monte-carlo](<https://devfeed.tech/tags/monte-carlo.md>), [operations-research](<https://devfeed.tech/tags/operations-research.md>), [optimization](<https://devfeed.tech/tags/optimization.md>), [paper](<https://devfeed.tech/tags/paper.md>), [probabilistic](<https://devfeed.tech/tags/probabilistic.md>), [risk](<https://devfeed.tech/tags/risk.md>), [simulation](<https://devfeed.tech/tags/simulation.md>), [zalando](<https://devfeed.tech/tags/zalando.md>), [zalando-science](<https://devfeed.tech/tags/zalando-science.md>)

### AI overview

Zalando describes a replenishment optimization engine that combines probabilistic demand forecasting, discrete event simulation, and stochastic optimization. Its extended (R, s, Q) policy adapts replenishment across a product's lifecycle while Monte Carlo simulation evaluates candidate policies under uncertainty.

### Source excerpt

Learn how the ZEOS replenishment optimization system achieves up to 22.1% GMV uplift by unifying probabilistic demand forecasting with risk-aware discrete event simulation.

## Building a Dynamic Inventory Optimization System

DevFeed: [Building a Dynamic Inventory Optimization System](<https://devfeed.tech/articles/building-a-dynamic-inventory-optimisation-system-a-deep-dive-47492.md>)

Original publisher: [Read original article](<https://engineering.zalando.com/posts/2025/06/inventory-optimisation-system.html>)

Author: Alva Presbitero

Published: 2025-06-29T22:00:00Z

Content type: article

Language: en

Sources: [Zalando](<https://devfeed.tech/sources/zalando-engineering-blog.md>)

Topics: [Optimization](<https://devfeed.tech/topics/optimization.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [decision-making](<https://devfeed.tech/topics/decision-making.md>), [Simulation](<https://devfeed.tech/topics/simulation.md>), [recommendation systems](<https://devfeed.tech/topics/recommendation-systems.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [applied-science](<https://devfeed.tech/tags/applied-science.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [aws](<https://devfeed.tech/tags/aws.md>), [backend](<https://devfeed.tech/tags/backend.md>), [building](<https://devfeed.tech/tags/building.md>), [cost-optimisation](<https://devfeed.tech/tags/cost-optimisation.md>), [data-science](<https://devfeed.tech/tags/data-science.md>), [deep-dive](<https://devfeed.tech/tags/deep-dive.md>), [demand-forecasting](<https://devfeed.tech/tags/demand-forecasting.md>), [e-commerce](<https://devfeed.tech/tags/e-commerce.md>), [lead-time](<https://devfeed.tech/tags/lead-time.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [monte-carlo](<https://devfeed.tech/tags/monte-carlo.md>), [operations-research](<https://devfeed.tech/tags/operations-research.md>), [optimization](<https://devfeed.tech/tags/optimization.md>), [pipelines](<https://devfeed.tech/tags/pipelines.md>), [probabilistic](<https://devfeed.tech/tags/probabilistic.md>), [recommendations](<https://devfeed.tech/tags/recommendations.md>), [scale](<https://devfeed.tech/tags/scale.md>), [zalando](<https://devfeed.tech/tags/zalando.md>), [zalando-science](<https://devfeed.tech/tags/zalando-science.md>)

### AI overview

This technical article explains a dynamic inventory optimization system for e-commerce replenishment. It covers probabilistic demand and lead-time forecasting, cost optimization, recommendation generation, Monte Carlo simulation, and scalable forecasting and policy optimization pipelines.

### Source excerpt

This technical blog outlines how we built a scalable inventory optimization system to help partners maintain a profitable inventory.

## Exploring the Potential of Graph Neural Networks to Transform Recommendations at Zalando

DevFeed: [Exploring the Potential of Graph Neural Networks to Transform Recommendations at Zalando](<https://devfeed.tech/articles/exploring-the-potential-of-graph-neural-networks-to-transform-recommendations-at-zalando-47484.md>)

Original publisher: [Read original article](<https://engineering.zalando.com/posts/2024/12/gnn-recommendations-zalando.html>)

Author: Mariia Bulycheva

Published: 2024-12-18T23:00:00Z

Content type: article

Language: en

Sources: [Zalando](<https://devfeed.tech/sources/zalando-engineering-blog.md>)

Topics: [recommendation systems](<https://devfeed.tech/topics/recommendation-systems.md>), [Graphs](<https://devfeed.tech/topics/graphs.md>), [Neural Network](<https://devfeed.tech/topics/neural-network.md>), [Embeddings](<https://devfeed.tech/topics/embeddings.md>)

Tags: [customers](<https://devfeed.tech/tags/customers.md>), [deep-learning](<https://devfeed.tech/tags/deep-learning.md>), [embeddings](<https://devfeed.tech/tags/embeddings.md>), [graph](<https://devfeed.tech/tags/graph.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [neural-networks](<https://devfeed.tech/tags/neural-networks.md>), [recommendations](<https://devfeed.tech/tags/recommendations.md>), [recommender-systems](<https://devfeed.tech/tags/recommender-systems.md>), [research](<https://devfeed.tech/tags/research.md>), [zalando](<https://devfeed.tech/tags/zalando.md>), [zalando-science](<https://devfeed.tech/tags/zalando-science.md>)

### AI overview

Zalando explores integrating graph neural networks into its homepage recommender system. The approach models users and content as a bipartite graph, predicts future interactions, and generates embeddings that can be added to the existing production model.

### Source excerpt

Delivering personalized recommendations is key to engaging Zalando's customers, but traditional models can miss the complexity of user-content interactions. By integrating graph neural networks (GNNs), we're exploring a cutting-edge approach to better predict clicks and enhance the shopping experience.

## Paper Announcement: Leveraging Multimodal LLMs for Large-Scale Product Retrieval Evaluation

DevFeed: [Paper Announcement: Leveraging Multimodal LLMs for Large-Scale Product Retrieval Evaluation](<https://devfeed.tech/articles/paper-announcement-leveraging-multimodal-llms-for-large-scale-product-retrieval-evaluation-47483.md>)

Original publisher: [Read original article](<https://engineering.zalando.com/posts/2024/11/llm-as-a-judge-relevance-assessment-paper-announcement.html>)

Author: Kasra Hosseini

Published: 2024-11-14T23:00:00Z

Content type: article

Language: en

Sources: [Zalando](<https://devfeed.tech/sources/zalando-engineering-blog.md>)

Topics: [LLM evaluation / benchmarking](<https://devfeed.tech/topics/llm-evaluation-benchmarking.md>), [multimodal-ai](<https://devfeed.tech/topics/multimodal-ai.md>), [information retrieval](<https://devfeed.tech/topics/information-retrieval.md>), [search-engines](<https://devfeed.tech/topics/search-engines.md>), [AI-generated research reports](<https://devfeed.tech/topics/ai-generated-research-reports.md>)

Tags: [backend](<https://devfeed.tech/tags/backend.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [llm](<https://devfeed.tech/tags/llm.md>), [llm-as-a-judge](<https://devfeed.tech/tags/llm-as-a-judge.md>), [llms](<https://devfeed.tech/tags/llms.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [multimodal](<https://devfeed.tech/tags/multimodal.md>), [product-search](<https://devfeed.tech/tags/product-search.md>), [research](<https://devfeed.tech/tags/research.md>), [retrieval](<https://devfeed.tech/tags/retrieval.md>), [search](<https://devfeed.tech/tags/search.md>), [zalando](<https://devfeed.tech/tags/zalando.md>), [zalando-science](<https://devfeed.tech/tags/zalando-science.md>)

### AI overview

A research paper presents a multimodal LLM-based framework for evaluating product retrieval relevance at scale. The approach uses LLMs to generate annotation guidelines and assess query-product relevance, comparing results with human annotations across English and German production search queries.

### Source excerpt

Sharing our latest research paper on leveraging LLM-as-a-Judge for scalable, multimodal relevance assessment in e-commerce product search.

## Paper Announcement: Joint Order Selection, Allocation, Batching and Picking for Large Scale Warehouses

DevFeed: [Paper Announcement: Joint Order Selection, Allocation, Batching and Picking for Large Scale Warehouses](<https://devfeed.tech/articles/paper-announcement-joint-order-selection-allocation-batching-and-picking-for-large-scale-warehouses-47466.md>)

Original publisher: [Read original article](<https://engineering.zalando.com/posts/2024/01/paper-warehouse-order-batching.html>)

Author: Julius Pätzold

Published: 2024-01-28T23:00:00Z

Content type: release

Language: en

Sources: [Zalando](<https://devfeed.tech/sources/zalando-engineering-blog.md>)

Topics: [Algorithms](<https://devfeed.tech/topics/algorithms.md>), [Optimization](<https://devfeed.tech/topics/optimization.md>), [Benchmark](<https://devfeed.tech/topics/benchmark.md>), [GitHub](<https://devfeed.tech/topics/github.md>), [implementation](<https://devfeed.tech/topics/implementation.md>), [Software](<https://devfeed.tech/topics/software.md>)

Tags: [backend](<https://devfeed.tech/tags/backend.md>), [batching](<https://devfeed.tech/tags/batching.md>), [github](<https://devfeed.tech/tags/github.md>), [large](<https://devfeed.tech/tags/large.md>), [logistics](<https://devfeed.tech/tags/logistics.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [operations-research](<https://devfeed.tech/tags/operations-research.md>), [optimization](<https://devfeed.tech/tags/optimization.md>), [orders](<https://devfeed.tech/tags/orders.md>), [paper](<https://devfeed.tech/tags/paper.md>), [scale](<https://devfeed.tech/tags/scale.md>), [zalando](<https://devfeed.tech/tags/zalando.md>), [zalando-science](<https://devfeed.tech/tags/zalando-science.md>)

### AI overview

Zalando announces a research paper on jointly optimizing order selection, item allocation, batching, and picking in large-scale warehouse operations. The paper provides benchmark instances, two baseline algorithms, and a validation tool, with implementations available on GitHub.

### Source excerpt

Sharing our latest research paper on warehouse order batching.

## Applied Methods from Mathematical Optimization and Machine Learning in E-commerce

DevFeed: [Applied Methods from Mathematical Optimization and Machine Learning in E-commerce](<https://devfeed.tech/articles/applied-methods-from-mathematical-optimization-and-machine-learning-in-e-commerce-47452.md>)

Original publisher: [Read original article](<https://engineering.zalando.com/posts/2023/02/gor-workshop.html>)

Author: Amin Jorati

Published: 2023-02-20T23:00:00Z

Content type: article

Language: en

Sources: [Zalando](<https://devfeed.tech/sources/zalando-engineering-blog.md>)

Topics: [Optimization](<https://devfeed.tech/topics/optimization.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [Supply Chain Optimization Technologies (SCOT)](<https://devfeed.tech/topics/supply-chain-optimization-technologies-scot.md>)

Tags: [article](<https://devfeed.tech/tags/article.md>), [data-science](<https://devfeed.tech/tags/data-science.md>), [e-commerce](<https://devfeed.tech/tags/e-commerce.md>), [event](<https://devfeed.tech/tags/event.md>), [forecasting](<https://devfeed.tech/tags/forecasting.md>), [hybrid](<https://devfeed.tech/tags/hybrid.md>), [logistics](<https://devfeed.tech/tags/logistics.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [network-design](<https://devfeed.tech/tags/network-design.md>), [operations-research](<https://devfeed.tech/tags/operations-research.md>), [optimization](<https://devfeed.tech/tags/optimization.md>), [report](<https://devfeed.tech/tags/report.md>), [research](<https://devfeed.tech/tags/research.md>), [routing](<https://devfeed.tech/tags/routing.md>), [scheduling](<https://devfeed.tech/tags/scheduling.md>), [streaming](<https://devfeed.tech/tags/streaming.md>), [zalando](<https://devfeed.tech/tags/zalando.md>), [zalando-science](<https://devfeed.tech/tags/zalando-science.md>)

### AI overview

Zalando reports on a 2022 workshop about applying mathematical optimization and machine learning to e-commerce. Talks covered forecasting, network design, pricing, logistics, scheduling, and vehicle routing, alongside Zalando use cases involving large-scale discounting and stock distribution.

### Source excerpt

Report from a workshop hosted by Zalando in October 2022

## Zalando's Machine Learning Platform

DevFeed: [Zalando's Machine Learning Platform](<https://devfeed.tech/articles/zalando-s-machine-learning-platform-47444.md>)

Original publisher: [Read original article](<https://engineering.zalando.com/posts/2022/04/zalando-machine-learning-platform.html>)

Author: Krzysztof Szafranek

Published: 2022-04-18T22:00:00Z

Content type: article

Language: en

Sources: [Zalando](<https://devfeed.tech/sources/zalando-engineering-blog.md>)

Topics: [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [AI Development](<https://devfeed.tech/topics/ai-development.md>), [Developer Tools](<https://devfeed.tech/topics/developer-tools.md>), [data-engineering](<https://devfeed.tech/topics/data-engineering.md>), [recommendation systems](<https://devfeed.tech/topics/recommendation-systems.md>), [Apache Spark](<https://devfeed.tech/topics/spark.md>), [databricks](<https://devfeed.tech/topics/databricks.md>), [jupyterhub](<https://devfeed.tech/topics/jupyterhub.md>), [Jupyter Notebook](<https://devfeed.tech/topics/jupyter-notebook.md>), [Amazon S3](<https://devfeed.tech/topics/amazon-s3.md>), [BigQuery](<https://devfeed.tech/topics/bigquery.md>), [Computer vision](<https://devfeed.tech/topics/computer-vision.md>)

Tags: [apache-spark](<https://devfeed.tech/tags/apache-spark.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [aws](<https://devfeed.tech/tags/aws.md>), [backend](<https://devfeed.tech/tags/backend.md>), [bigquery](<https://devfeed.tech/tags/bigquery.md>), [data](<https://devfeed.tech/tags/data.md>), [databricks](<https://devfeed.tech/tags/databricks.md>), [experimentation](<https://devfeed.tech/tags/experimentation.md>), [gpu](<https://devfeed.tech/tags/gpu.md>), [high-performance-computing](<https://devfeed.tech/tags/high-performance-computing.md>), [jupyter](<https://devfeed.tech/tags/jupyter.md>), [jupyter-notebooks](<https://devfeed.tech/tags/jupyter-notebooks.md>), [jupyterhub](<https://devfeed.tech/tags/jupyterhub.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [machine-learning-platform](<https://devfeed.tech/tags/machine-learning-platform.md>), [tooling](<https://devfeed.tech/tags/tooling.md>), [zalando](<https://devfeed.tech/tags/zalando.md>), [zalando-science](<https://devfeed.tech/tags/zalando-science.md>)

### AI overview

Zalando describes the machine-learning platform supporting experimentation and large-scale data work. The platform includes hosted JupyterHub and Datalab environments, access to data sources such as S3 and BigQuery, Databricks for Apache Spark processing, and an HPC cluster with GPU nodes for demanding workloads.

### Source excerpt

Architecture and tooling behind machine learning at Zalando

## Tuning Image Classifiers using Human-In-The-Loop

DevFeed: [Tuning Image Classifiers using Human-In-The-Loop](<https://devfeed.tech/articles/tuning-image-classifiers-using-human-in-the-loop-47434.md>)

Original publisher: [Read original article](<https://engineering.zalando.com/posts/2021/10/tuning-image-classifiers-using-human-in-the-loop.html>)

Author: Paul O'Grady

Published: 2021-10-12T22:00:00Z

Content type: article

Language: en

Sources: [Zalando](<https://devfeed.tech/sources/zalando-engineering-blog.md>)

Topics: [Algorithms](<https://devfeed.tech/topics/algorithms.md>), [Computer vision](<https://devfeed.tech/topics/computer-vision.md>), [data](<https://devfeed.tech/topics/data.md>), [Code](<https://devfeed.tech/topics/code.md>)

Tags: [algorithm](<https://devfeed.tech/tags/algorithm.md>), [backend](<https://devfeed.tech/tags/backend.md>), [computer-vision](<https://devfeed.tech/tags/computer-vision.md>), [data](<https://devfeed.tech/tags/data.md>), [em](<https://devfeed.tech/tags/em.md>), [human-in-the-loop](<https://devfeed.tech/tags/human-in-the-loop.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [metric](<https://devfeed.tech/tags/metric.md>), [parameter](<https://devfeed.tech/tags/parameter.md>), [predictions](<https://devfeed.tech/tags/predictions.md>), [python](<https://devfeed.tech/tags/python.md>), [validation](<https://devfeed.tech/tags/validation.md>), [zalando](<https://devfeed.tech/tags/zalando.md>), [zalando-science](<https://devfeed.tech/tags/zalando-science.md>)

### AI overview

This article presents AutoThreshold, an Expectation-Maximization algorithm that uses human annotations to estimate image-classifier confidence thresholds for out-of-distribution images. It addresses performance degradation caused by shifts in product-image data and supports fashion-attribute search.

### Source excerpt

We present an Expectation-Maximization (EM) algorithm for iteratively estimating the optimal class-confidence threshold for an image classifier using human annotators. The algorithm is developed for classifiers that are applied to out-of-distribution images, and efficiently constructs a validation data set to estimate an optimal threshold for this use case.

## Space efficient machine learning feature stores using probabilistic data structures - a benchmark

DevFeed: [Space efficient machine learning feature stores using probabilistic data structures - a benchmark](<https://devfeed.tech/articles/space-efficient-machine-learning-feature-stores-using-probabilistic-data-structures-a-benchmark-47432.md>)

Original publisher: [Read original article](<https://engineering.zalando.com/posts/2021/10/space-efficient-machine-learning-feature-stores-using-probabilistic-data-structures.html>)

Author: Enno Shioji

Published: 2021-10-04T22:00:00Z

Content type: article

Language: en

Sources: [Zalando](<https://devfeed.tech/sources/zalando-engineering-blog.md>)

Topics: [feature-store](<https://devfeed.tech/topics/feature-store.md>), [recommendation systems](<https://devfeed.tech/topics/recommendation-systems.md>), [bloom-filter](<https://devfeed.tech/topics/bloom-filter.md>), [Data structures](<https://devfeed.tech/topics/data-structures.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [systems](<https://devfeed.tech/topics/systems.md>)

Tags: [backend](<https://devfeed.tech/tags/backend.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [bloom-filter](<https://devfeed.tech/tags/bloom-filter.md>), [data-structures](<https://devfeed.tech/tags/data-structures.md>), [feature-store](<https://devfeed.tech/tags/feature-store.md>), [infrastructure](<https://devfeed.tech/tags/infrastructure.md>), [latency](<https://devfeed.tech/tags/latency.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [ml](<https://devfeed.tech/tags/ml.md>), [network](<https://devfeed.tech/tags/network.md>), [performance](<https://devfeed.tech/tags/performance.md>), [recommender-systems](<https://devfeed.tech/tags/recommender-systems.md>), [scalability](<https://devfeed.tech/tags/scalability.md>), [zalando](<https://devfeed.tech/tags/zalando.md>), [zalando-science](<https://devfeed.tech/tags/zalando-science.md>)

### AI overview

This post describes a space-efficient machine-learning feature store using probabilistic data structures, including a Bloom filter as the backing data store. It benchmarks the approach as an alternative to key-value-store-based feature stores in certain situations.

### Source excerpt

In this post, we describe a technique for providing machine learning feature stores with sublinear space requirements, and perform a benchmark that uses bloom filter as the backing data store. Such feature stores can be an effective alternative to the commonly used key-value-store-based feature stores in certain situations.