The AI for Retail (AIR) Lab Amsterdam centered its research on three core themes: AI for search and recommendation, transparent AI for managing goods flows, and explainable AI.
To drive these advancements, the lab leverages key technical AI components, focusing primarily on:
With a commitment to explainable AI systems.
The AI for Retail (AIR) Lab Amsterdam was a joint industry-academic collaboration between the University of Amsterdam (UvA) and Ahold Delhaize, dedicated to advancing human-centered and socially responsible artificial intelligence for retail environments.
The lab’s mission and vision focused on developing fundamental knowledge in information retrieval, recommender systems, and conversational assistants through data-driven and machine learning-based approaches. By placing people at the core of its strategy, the lab aimed to augment human abilities, address broader societal needs, and advance transparent AI technologies for managing goods flows and consumer experiences.
The impact of the lab was centered on bridging scientific research with real-world application, experimentally validating new algorithms, models, and evaluation methodologies directly within live retail settings. Furthermore, AIR Lab drove long-term value by evaluating the societal influence of its technologies and developing talent through dedicated academic and industry tracks.
A Comprehensive Taxonomy of Negation for NLP and Neural Retrievers Proceedings Article
In: Findings of the Association for Computational Linguistics: EMNLP 2025, pp. 15511–15533, ACL, 2025.
Scalable Data Debugging for Neighborhood-based Recommendation with Data Shapley Values Proceedings Article
In: RecSys 2025: 19th ACM Conference on Recommender Systems, pp. 441–450, ACM, 2025.
Generative Retrieval for Book Search Proceedings Article
In: KDD 2025: 31st SIGKDD Conference on Knowledge Discovery and Data Mining, pp. 2606–2617, ACM, 2025.
A Comprehensive Taxonomy of Negation for NLP and Neural Retrievers Journal Article
In: arXiv preprint arXiv:2507.22337, 2025.
Benchmark Granularity and Model Robustness for Image-Text Retrieval: A Reproducibility Study Proceedings Article
In: SIGIR 2025: 48th international ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 3183-3193, ACM, 2025.
Boosting Retrieval-Augmented Generation with Generation-Augmented Retrieval: A Co-Training Approach Proceedings Article
In: SIGIR 2025: 48th international ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 2441-2451, ACM, 2025.
Lightweight and Direct Document Relevance Optimization for Generative Information Retrieval Proceedings Article
In: SIGIR 2025: 48th international ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 1327-1338, ACM, 2025.
Augmentation with Neighboring Information for Conversational Recommendation Journal Article
In: ACM Transactions on Information Systems, vol. 43, no. 3, pp. Article 62, 2025.
Lightweight and Direct Document Relevance Optimization for Generative Information Retrieval Journal Article
In: arXiv preprint arXiv:2504.05181, 2025.
Repeat-bias-aware Optimization of Beyond-accuracy Metrics for Next Basket Recommendation Proceedings Article
In: ECIR 2025: 47th European Conference on Information Retrieval (Part I), pp. 214–229, Springer, 2025.
Understanding Visual Saliency of Outlier Items in Product Search Journal Article
In: arXiv preprint arXiv:2503.23596, 2025.
Declarative Machine Learning Pipeline Management via Logical Query Plans PhD Thesis
University of Amsterdam, 2025.
Expanding Boundaries in Scalable Session-Based Recommendations PhD Thesis
University of Amsterdam, 2025.
Generative Retrieval for Book Search Journal Article
In: arXiv preprint:2501.11034, 2025.
Learning to Rank for e-Commerce Search PhD Thesis
University of Amsterdam, 2025.
Report on the 2nd Search Futures Workshop at ECIR 2025 Journal Article
In: ACM SIGIR Forum, vol. 59, no. 1, 2025.
Learning Latent Spaces for Domain Generalization in Time Series Forecasting Journal Article
In: arXiv preprint arXiv:2412.11171, 2024.
Hierarchical Forecasting at Scale Journal Article
In: International Journal of Forecasting, vol. 40, no. 4, pp. 1689–1700, 2024.
Advances in Human Event Modeling: From Graph Neural Networks to Language Models Proceedings Article
In: KDD 2024: 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, pp. 6459–6469, ACM, 2024.
Demonstrating and Reducing Shortcuts in Vision-Language Representation Learning Journal Article
In: Transactions on Machine Learning Research, 2024.
Snapcase - Regain Control over Your Predictions with Low-Latency Machine Unlearning Proceedings Article
In: Proceedings of the VLDB, pp. 4273–4276, 2024.
Are We Really Achieving Better Beyond-Accuracy Performance in Next Basket Recommendation? Proceedings Article
In: SIGIR 2024: 47th international ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 924–934, ACM, 2024.
ETUDE – Evaluating the Inference Latency of Session-Based Recommendation Models at Scale Proceedings Article
In: ICDE 2024: The 40th IEEE International Conference on Data Engineering, pp. 5177–5183, IEEE, 2024.
Measuring Item Fairness in Next Basket Recommendation: A Reproducibility Study Proceedings Article
In: ECIR 2024: 46th European Conference on Information Retrieval, Part IV, pp. 210–225, Springer, 2024.
Multi-Modal Learned Sparse Retrieval with Probabilistic Expansion Control Proceedings Article
In: ECIR 2024: 46th European Conference on Information Retrieval, Part II, pp. 448–464, Springer, 2024.
Domain Generalization in Time Series Forecasting Journal Article
In: ACM Transactions on Knowledge Discovery from Data, vol. 18, no. 5, pp. Article 113, 2024.
Assisted design of data science pipelines Journal Article
In: The VLDB Journal, 2024.
Automated data cleaning can hurt fairness in machine learning-based decision making Journal Article
In: IEEE Transactions on Knowledge and Data Engineering, 2024.
Directions towards efficient and automated data wrangling with large language models Proceedings Article
In: 2024 IEEE 40th International Conference on Data Engineering Workshops (ICDEW), pp. 301-304, IEEE, 2024.
Efficient and Accurate Forecasting in Large-scale Settings PhD Thesis
University of Amsterdam, 2024.
Frequency adaptive normalization for non-stationary time series forecasting Proceedings Article
In: Advances in Neural Information Processing Systems (NeurIPS), 2024.
Multimodal machine learning for information retrieval: A vision and language perspective Miscellaneous
2024, (UvA).
Red Onions, Soft Cheese and Data: From Food Safety to Data Traceability for Responsible AI. Journal Article
In: IEEE Data Engineering Bulletin, 2024.
Repetition and exploration in recommendation PhD Thesis
University of Amsterdam, 2024.
Report on the 1st Workshop on Generative Information Retrieval (Gen-IR 2023) at SIGIR 2023 Journal Article
In: ACM SIGIR Forum, 2024.
Schemapile: A large collection of relational database schemas Proceedings Article
In: Proceedings of the ACM SIGMOD International Conference on Management of Data, ACM, 2024.
Towards Interactively Improving ML Data Preparation Code via Proceedings Article
In: Proceedings of the Eighth Workshop on Data Management for End-to-End Machine Learning, pp. 7–11, ACM, 2024.
Repetition and Exploration in Offline Reinforcement Learning-based Recommendations Proceedings Article
In: 4th Workshop on Deep Reinforcement Learning for Information Retrieval at CIKM 2023, ACM, 2023.
A Next Basket Recommendation Reality Check Journal Article
In: ACM Transactions on Information Systems, vol. 41, no. 4, pp. Article 116, 2023.
Masked and Swapped Sequence Modeling for Next Novel Basket Recommendation in Grocery Shopping Proceedings Article
In: RecSys 2023: 17th ACM Conference on Recommender Systems, ACM, 2023.
Complex Item Set Recommendation Proceedings Article
In: SIGIR 2023: 46th international ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 3444–3447, ACM, 2023.
Forget Me Now: Fast and Exact Unlearning in Neighborhood-based Recommendation Proceedings Article
In: SIGIR 2023: 46th international ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 2011–2015, ACM, 2023.
On the Impact of Outlier Bias on User Clicks Proceedings Article
In: SIGIR 2023: 46th international ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 18–27, ACM, 2023.
Repetition and Exploration in Sequential Recommendation Proceedings Article
In: SIGIR 2023: 46th international ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 2532–2541, ACM, 2023.
Who Will Purchase this Item Next? Reverse Next Period Recommendation in Grocery Shopping Journal Article
In: ACM Transactions on Recommender Systems, vol. 1, no. 2, pp. Article 10, 2023.
Distributional Reinforcement Learning with Dual Expectile-Quantile Regression Journal Article
In: arXiv preprint arXiv:2305.16877, 2023.
A Simulation Environment and Reinforcement Learning Method for Waste Reduction Journal Article
In: Transactions on Machine Learning Research, 2023.
Scene-centric vs. Object-centric Image-Text Cross-modal Retrieval: A Reproducibility Study Proceedings Article
In: ECIR 2023: 45th European Conference on Information Retrieval, pp. 68–85, Springer, 2023.
How to Make an Outlier? Studying the Effect of Presentational Features on the Outlierness of Items in Product Search Results Proceedings Article
In: 2023 ACM SIGIR Conference on Human Information Interaction & Retrieval (CHIIR 2023), pp. 346–350, ACM, 2023.
A Personalized Neighborhood-based Model for Within-basket Recommendation in Grocery Shopping Proceedings Article
In: WSDM 2023: The Sixteenth International Conference on Web Search and Data Mining, pp. 87–95, ACM, 2023.
Ahold Delhaize is a Dutch-Belgian multinational retail and wholesale holding company.
University of Amsterdam (UvA) is the Netherlands’ largest university, offering the widest range of academic programmes.
