# Free Lunch! Retrospective Uplift Modeling for Dynamic Promotions Recommendation within ROI Constraints

arXiv: https://arxiv.org/abs/2008.06293 · HTML: https://mlsanity.com/paper/2008.06293/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Aug 2020.

## Built on by (most cited first, 20 of 20)

- [Explicit Feature Interaction-aware Uplift Network for Online Marketing](https://mlsanity.com/paper/2306.00315/) (2023)
- [E-Commerce Promotions Personalization via Online Multiple-Choice Knapsack with Uplift Modeling](https://mlsanity.com/paper/2108.13298/) (2021)
- [LBCF: A Large-Scale Budget-Constrained Causal Forest Algorithm](https://mlsanity.com/paper/2201.12585/) (2022)
- [End-to-End Cost-Effective Incentive Recommendation under Budget Constraint with Uplift Modeling](https://mlsanity.com/paper/2408.11623/) (2024)
- [An End-to-End Framework for Marketing Effectiveness Optimization under Budget Constraint](https://mlsanity.com/paper/2302.04477/) (2023)
- [Benchmarking PtO and PnO Methods in the Predictive Combinatorial Optimization Regime](https://mlsanity.com/paper/2311.07633/) (2023)
- [Uplift Modeling: from Causal Inference to Personalization](https://mlsanity.com/paper/2308.09066/) (2023)
- [Causality from Bottom to Top: A Survey](https://mlsanity.com/paper/2403.11219/) (2024)
- [Incremental Profit per Conversion: a Response Transformation for Uplift Modeling in E-Commerce Promotions](https://mlsanity.com/paper/2306.13759/) (2023)
- [Benchmarking for Deep Uplift Modeling in Online Marketing](https://mlsanity.com/paper/2406.00335/) (2024)
- [Improve ROI with Causal Learning and Conformal Prediction](https://mlsanity.com/paper/2407.01065/) (2024)
- [Distribution-consistency Structural Causal Models](https://mlsanity.com/paper/2401.15911/) (2024)
- [Machine Learning Prescriptive Canvas for Optimizing Business Outcomes](https://mlsanity.com/paper/2206.10333/) (2022)
- [Enhancing Uplift Modeling in Multi-Treatment Marketing Campaigns: Leveraging Score Ranking and Calibration Techniques](https://mlsanity.com/paper/2408.13628/) (2024)
- [Segment Discovery: Enhancing E-commerce Targeting](https://mlsanity.com/paper/2409.13847/) (2024)
- [Qini Curve Estimation under Clustered Network Interference](https://mlsanity.com/paper/2502.20097/) (2025)
- [Guardrailed Uplift Targeting: A Causal Optimization Playbook for Marketing Strategy](https://mlsanity.com/paper/2512.19805/) (2025)
- [VALOR: Value-Aware Revenue Uplift Modeling with Treatment-Gated Representation for B2B Sales](https://mlsanity.com/paper/2604.02472/) (2026)
- [Budget-Constrained Causal Bandits: Bridging Uplift Modeling and Sequential Decision-Making](https://mlsanity.com/paper/2604.26169/) (2026)
- [Generative Optimization for Incentivized Advertising with Global Level Constraints](https://mlsanity.com/paper/2608.04421/) (2026)

## Abstract (arXiv)

Promotions and discounts have become key components of modern e-commerce platforms. For online travel platforms (OTPs), popular promotions include room upgrades, free meals and transportation services. By offering these promotions, customers can get more value for their money, while both the OTP and its travel partners may grow their loyal customer base. However, the promotions usually incur a cost that, if uncontrolled, can become unsustainable. Consequently, for a promotion to be viable, its associated costs must be balanced by incremental revenue within set financial constraints. Personalized treatment assignment can be used to satisfy such constraints. This paper introduces a novel uplift modeling technique, relying on the Knapsack Problem formulation, that dynamically optimizes the incremental treatment outcome subject to the required Return on Investment (ROI) constraints. The technique leverages Retrospective Estimation, a modeling approach that relies solely on data from positive outcome examples. The method also addresses training data bias, long term effects, and seasonality challenges via online-dynamic calibration. This approach was tested via offline experiments and online randomized controlled trials at Booking .com - a leading OTP with millions of customers worldwide, resulting in a significant increase in the target outcome while staying within the required financial constraints and outperforming other approaches.