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

Albert, Javier; Goldenberg, Dmitri

doi:10.1145/3511808.3557100

Cited by 10 publications

(7 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A popular way of allocating budget is to follow a two-stage paradigm [2,3,9,21,32,38]: in the first stage uplift models are used to predict the treatment effects, and in the second stage integer programming is invoked to find the optimal allocation. For instance, Zhao et al [38] propose to use a logit response model [26] to predict treatment effects and then obtain the optimal allocation via root-finding for KKT conditions.…”

Section: Related Work 21 Budget Allocationmentioning

confidence: 99%

“…Makhijani et al [21] formulate the marketing goal as a Min-Cost Flow network optimization problem for better expressivity. More recently, Ai et al [2], Albert and Goldenberg [3] use MCKP to represent the budget allocation problem in the discrete case and develop efficient solvers based on Lagrangian duality. Though effective, owing to the misalignment between the objectives of these two stages, solutions from these two-stage methods could be suboptimal.…”

Section: Related Work 21 Budget Allocationmentioning

confidence: 99%

“…As discussed, a lot of efforts have been devoted to two-stage budget allocation methods [2,3,9,21,32,38]. In this section, we briefly introduce common components in two-stage budget allocation methods.…”

Section: The Two-stage Paradigmmentioning

confidence: 99%

“…Offering incentives (e.g., cash bonuses, discounts, coupons) to consumers are effective ways for online platforms to acquire new users, increase user engagement, and boost platform revenue [2,3,9,20,21,32,37,38,40,41]. For example, coupons in Taobao [37] are offered to increase user activity, promotions in Booking [9] can improve user satisfaction, cash bonuses in Kuaishou [2] are used to stimulate user retention, and promotions in Uber [40] can encourage users to start using a new product.…”

Section: Introductionmentioning

confidence: 99%

“…Many recent advances address the budget allocation problem using a two-stage paradigm [2,3,32,38]: in the first stage the individual-level heterogeneous treatment effects are estimated using causal inference techniques, and then the estimated effects are fed into an integer programming formulation as coefficients to find the optimal allocation. However, the objectives of these two stages are fundamentally different, and in practice, we have observed these objectives are not perfectly aligned.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

An End-to-End Framework for Marketing Effectiveness Optimization under Budget Constraint

Yan¹,

Wang²,

Zhou³

et al. 2023

Preprint

View full text Add to dashboard Cite

Online platforms often incentivize consumers to improve user engagement and platform revenue. Since different consumers might respond differently to incentives, individual-level budget allocation is an essential task in marketing campaigns. Recent advances in this field often address the budget allocation problem using a two-stage paradigm: the first stage estimates the individual-level treatment effects using causal inference algorithms, and the second stage invokes integer programming techniques to find the optimal budget allocation solution. Since the objectives of these two stages might not be perfectly aligned, such a two-stage paradigm could hurt the overall marketing effectiveness.In this paper, we propose a novel end-to-end framework to directly optimize the business goal under budget constraints. Our core idea is to construct a regularizer to represent the marketing goal and optimize it efficiently using gradient estimation techniques. As such, the obtained models can learn to maximize the marketing goal directly and precisely. We extensively evaluate our proposed method in both offline and online experiments, and experimental results demonstrate that our method outperforms current stateof-the-art methods. Our proposed method is currently deployed to allocate marketing budgets for hundreds of millions of users on a short video platform and achieves significant business goal improvements. Our code will be publicly available.

show abstract