mlsanityData to 7 Oct 2026

E-Commerce Promotions Personalization via Online Multiple-Choice Knapsack with Uplift Modeling

arXiv 2108.13298 ↗First posted 11 Aug 2021cs.IR cs.AI cs.LGcited by 21

Not on the map. Why?

Abstract (arXiv)

Promotions and discounts are essential components of modern e-commerce platforms, where they are often used to incentivize customers towards purchase completion. Promotions also affect revenue and may incur a monetary loss that is often limited by a dedicated promotional budget. We study the Online Constrained Multiple-Choice Promotions Personalization Problem, where the optimization goal is to select for each customer which promotion to present in order to maximize purchase completions, while also complying with global budget limitations. Our work formalizes the problem as an Online Multiple Choice Knapsack Problem and extends the existent literature by addressing cases with negative weights and values. We provide a real-time adaptive method that guarantees budget constraints compliance and achieves above 99.7% of the optimal promotional impact on various datasets. Our method is evaluated on a large-scale experimental study at one of the leading online travel platforms in the world.

Key facts. Cited by 21 papers in the map (data through 7 Oct 2026). Builds on 11 of its 44 references that are in the map. First posted on arXiv 11 Aug 2021.

Builds on

11 of 44 references.

References · 11

  1. 2017Meta-learners for Estimating Heterogeneous Treatment Effects using Machine Learningcited by 475
  2. 2017Causal Effect Inference with Deep Latent-Variable Modelscited by 408
  3. 2016Learning Representations for Counterfactual Inferencecited by 327
  4. 2013Bandits with Knapsackscited by 163
  5. 2019A Unified Framework for Marketing Budget Allocationcited by 33
  6. 2019Uplift Modeling for Multiple Treatments with Cost Optimizationcited by 25
  7. 2020Free Lunch! Retrospective Uplift Modeling for Dynamic Promotions Recommendation within ROI Constraintscited by 20
  8. 2020Spending Money Wisely: Online Electronic Coupon Allocation based on Real-Time User Intent Detectioncited by 13
  9. 2019Cost-Effective Incentive Allocation via Structured Counterfactual Inferencecited by 12
  10. 2017Democratizing online controlled experiments at Booking.comcited by 5
  11. 2021To do or not to do: cost-sensitive causal decision-makingcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 5; 2024: 4; 2025: 5; 2026: 6.

21 papers.

Sort:

  1. 2023Explicit Feature Interaction-aware Uplift Network for Online Marketingcited by 25
  2. 2024End-to-End Cost-Effective Incentive Recommendation under Budget Constraint with Uplift Modelingcited by 10
  3. 2023An End-to-End Framework for Marketing Effectiveness Optimization under Budget Constraintcited by 9
  4. 2024Decision Focused Causal Learning for Direct Counterfactual Marketing Optimizationcited by 9
  5. 2023Uplift Modeling: from Causal Inference to Personalizationcited by 5
  6. 2022Personalized Promotion Decision Making Based on Direct and Enduring Effect Predictionscited by 4
  7. 2023Maximizing the Success Probability of Policy Allocations in Online Systemscited by 4
  8. 2023Incremental Profit per Conversion: a Response Transformation for Uplift Modeling in E-Commerce Promotionscited by 3
  9. 2024Benchmarking for Deep Uplift Modeling in Online Marketingcited by 3
  10. 2025Bi-Level Decision-Focused Causal Learning for Large-Scale Marketing Optimization: Bridging Observational and Experimental Datacited by 2
  11. 2025SACO: Sequence-Aware Constrained Optimization Framework for Coupon Distribution in E-commercecited by 1
  12. 2026Evaluating Uplift Modeling under Structural Biases: Insights into Metric Stability and Model Robustnesscited by 1
9 more
  1. 2024Segment Discovery: Enhancing E-commerce Targetingcited by 0
  2. 2025Maturity Framework for Enhancing Machine Learning Qualitycited by 0
  3. 2025Hidden Representation Clustering with Multi-Task Representation Learning towards Robust Online Budget Allocationcited by 0
  4. 2025Guardrailed Uplift Targeting: A Causal Optimization Playbook for Marketing Strategycited by 0
  5. 2026VALOR: Value-Aware Revenue Uplift Modeling with Treatment-Gated Representation for B2B Salescited by 0
  6. 2026Budget-Constrained Causal Bandits: Bridging Uplift Modeling and Sequential Decision-Makingcited by 0
  7. 2026Generative Optimization for Incentivized Advertising with Global Level Constraintscited by 0
  8. 2026FunnelCausalNet: Funnel-aware Joint Conversion-Revenue Uplift for Multi-tier Coupon Allocationcited by 0
  9. 2026A General Framework for Budgeted Threshold Incentives on Requestcited by 0