Serenade - Low-Latency Session-Based Recommendation in e-Commerce at Scale
Summary: Serenade uses VMIS-kNN with a prebuilt index for session-based next-item prediction at scale, overcoming exponential session space. Production bol.com demonstrates ~1000 req/s and sub-7 ms 90th percentile latency across millions of items and 45M sessions. (summarized by gpt-5-nano on Feb 09 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Barrie Kersbergen (bol.com)
- 2. Olivier Sprangers (University of Amsterdam)
- 3. Sebastian Schelter (University of Amsterdam)
BibTeX Citation
@inproceedings{kersbergen_sigmod22,
title = {{Serenade - Low-Latency Session-Based Recommendation in e-Commerce at Scale}},
author = {Kersbergen, Barrie and Sprangers, Olivier and Schelter, Sebastian},
series = {{SIGMOD} '22},
booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
publisher = {Association for Computing Machinery},
doi = {10.1145/3514221.3517901},
url = {https://dl.acm.org/doi/10.1145/3514221.3517901},
year = {2022}
}
Incoming Citations (Sorted by Pagerank)
Showing 2 of 2 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 8,651 | Cohesiveness-aware Hierarchical Compressed Index for Community Search on Attributed Graphs | 2025 | SIGMOD | 5.2929907e-05 |
| 10,048 | The Image Calculator: 10x Faster Image-AI Inference by Replacing JPEG with Self-designing Storage Format | 2024 | SIGMOD | 5.0896901e-05 |
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 5 of 5 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 71 | DuckDB: an Embeddable Analytical Database | 2019 | SIGMOD | 0.00037724477 |
| 442 | Differential dataflow | 2013 | CIDR | 0.00018201988 |
| 2,688 | CoHadoop: Flexible Data Placement and Its Exploitation in Hadoop | 2011 | VLDB | 8.1262948e-05 |
| 2,991 | StreamRec: A Real-Time Recommender System | 2011 | SIGMOD | 7.7708588e-05 |
| 4,629 | TencentRec: Real-time Stream Recommendation in Practice | 2015 | SIGMOD | 6.4938002e-05 |
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 9,123 | COSMO: A Large-Scale E-commerce Common Sense Knowledge Generation and Serving System at Amazon | 2024 | SIGMOD |
| 2 | 838 | Improving Approximate Nearest Neighbor Search through Learned Adaptive Early Termination | 2020 | SIGMOD |
| 3 | 2,682 | Accelerating Recommendation System Training by Leveraging Popular Choices | 2022 | VLDB |
| 4 | 1,373 | High-Throughput Vector Similarity Search in Knowledge Graphs | 2023 | SIGMOD |
| 5 | 4,987 | LANNS: A Web-Scale Approximate Nearest Neighbor Lookup System | 2022 | VLDB |
| 6 | 12,114 | CONCIERGE: Improving Constrained Search Results by Data Melioration | 2020 | VLDB |
| 7 | 11,627 | Snapcase – Regain Control over Your Predictions with Low-Latency Machine Unlearning | 2024 | VLDB |
| 8 | 5,569 | Supercharging Recommender Systems using Taxonomies for Learning User Purchase Behavior | 2012 | VLDB |
| 9 | 12,502 | Show Me the Money: Dynamic Recommendations for Revenue Maximization | 2014 | VLDB |
| 10 | 8,017 | ItemSuggest: A Data Management Platform for Machine Learned Ranking Services | 2019 | CIDR |