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

Goldenberg, Dmitri; Albert, Javier; Bernardi, Lucas; Estévez, P. A.

doi:10.1145/3383313.3412215

Cited by 20 publications

(15 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For each customer 𝑖 and each of the possible promotions 𝑘 ∈ 𝐾 𝑖 we can estimate CATE 𝑌 (𝑖, 𝑘) and CATE L (𝑖, 𝑘) using uplift modeling on data gathered from randomized controlled trials, similarly to our previous work [7]. The base item 𝑘 = 0 for which CATE 𝑌 (𝑖, 0) = 0 and CATE L (𝑖, 0) = 0 represents no promotion.…”

Section: Treatment Effect Estimationmentioning

confidence: 99%

“…A dedicated budget usually limits this incremental net revenue loss. The promotional campaign can remain sustainable as long as the overall incremental net revenue loss is within this budget [7].…”

Section: Introductionmentioning

confidence: 99%

“…In previous work [7] we addressed the causal estimation and binary promotion allocation problem, where we introduced the Retrospective Estimation technique. The proposed solution presents a dynamic system, similar to the Online Knapsack problem [18], that can decide whether a promotion should be assigned to a customer based on the CATE estimations.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

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

Albert¹,

Goldenberg²

2021

Preprint

Self Cite

View full text Add to dashboard Cite

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 Booking.comone of the leading online travel platforms in the world.

show abstract

Section: Treatment Effect Estimationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

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

Albert¹,

Goldenberg²

2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Thus, finding the fashion trends on a specific user group is particularly significant, which we call community trend prediction in this paper. These community trends play an important role in many applications such as community search [24,31], promotion recommendation [13,19,37], group recommendation [6,33].…”

Section: Introductionmentioning

confidence: 99%

Community Trend Prediction on Heterogeneous Graph in E-commerce

Yuan

Zou

et al. 2022

Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining

View full text Add to dashboard Cite

In online shopping, ever-changing fashion trends make merchants need to prepare more differentiated products to meet the diversified demands, and e-commerce platforms need to capture the market trend with a prophetic vision. For the trend prediction, the attribute tags, as the essential description of items, can genuinely reflect the decision basis of consumers. However, few existing works explore the attribute trend in the specific community for e-commerce. In this paper, we focus on the community trend prediction on the item attribute and propose a unified framework that combines the dynamic evolution of two graph patterns to predict the attribute trend in a specific community. Specifically, we first design a communityattribute bipartite graph at each time step to learn the collaboration of different communities. Next, we transform the bipartite graph into a hypergraph to exploit the associations of different attribute tags in one community. Lastly, we introduce a dynamic evolution component based on the recurrent neural networks to capture the fashion trend of attribute tags. Extensive experiments on three real-world datasets in a large e-commerce platform show the superiority of the proposed approach over several strong alternatives and demonstrate the ability to discover the community trend in advance. CCS CONCEPTS• Applied computing → Electronic commerce; • Information systems → Evaluation of retrieval results.

show abstract

“…Conducting marketing campaigns by giving away incentives is a popular and effective way [18] to boost user engagement and platform revenue, for example, discounts [13] in ride-sharing (Uber [31], Didi) and coupons in e-commerce (Alibaba [29], Booking.com [6,14]).…”

Section: Introductionmentioning

confidence: 99%

LBCF: A Large-Scale Budget-Constrained Causal Forest Algorithm

Ai,

Li,

Gong

et al. 2022

Preprint

View full text Add to dashboard Cite

Offering incentives (e.g., coupons at Amazon, discounts at Uber and video bonuses at Tiktok) to user is a common strategy used by online platforms to increase user engagement and platform revenue. Despite its proven effectiveness, these marketing incentives incur an inevitable cost and might result in a low ROI (Return on Investment) if not used properly. On the other hand, different users respond differently to these incentives, for instance, some users never buy certain products without coupons, while others do anyway. Thus, how to select the right amount of incentives (i.e. treatment) to each user under budget constraints is an important research problem with great practical implications. In this paper, we call such problem as a budget-constrained treatment selection (BTS) problem.The challenge is how to efficiently solve BTS problem on a Large-Scale dataset and achieve improved results over the existing techniques. We propose a novel tree-based treatment selection technique under budget constraints, called Large-Scale Budget-Constrained Causal Forest (LBCF) algorithm, which is also an efficient treatment selection algorithm suitable for modern distributed computing systems. A novel offline evaluation method is also proposed to overcome an intrinsic challenge in assessing solutions' performance for BTS problem in randomized control trials (RCT) data. We deploy our approach in a real-world scenario on a largescale video platform, where the platform gives away bonuses in order to increase users' campaign engagement duration. The simulation analysis, offline and online experiments all show that our method outperforms various tree-based state-of-the-art baselines 1 . The proposed approach is currently serving over hundreds of millions of users on the platform and achieves one of the most tremendous improvements over these months.

show abstract

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

Cited by 20 publications

References 21 publications

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

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

Community Trend Prediction on Heterogeneous Graph in E-commerce

LBCF: A Large-Scale Budget-Constrained Causal Forest Algorithm

Contact Info

Product

Resources

About