A survey and benchmarking study of multitreatment uplift modeling

• Published in: Data mining and knowledge discovery Vol. 34; no. 2; pp. 273 - 308
• Main Authors: Olaya, Diego, Coussement, Kristof, Verbeke, Wouter
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.03.2020; Springer Nature B.V
• Subjects: Academic Surveys and Tutorials; Artificial Intelligence; Benchmarks; Chemistry and Earth Sciences; Computer Science; Data Mining and Knowledge Discovery; Decision making; Information Storage and Retrieval; Modelling; Optimization; Performance evaluation; Physics; Pretreatment; Statistics for Engineering; Uplift; Matching; Prescriptive analytics; Causality; Literature survey; Business analytics; Uplift modeling
• ISSN: 1384-5810; 1573-756X
• DOI: 10.1007/s10618-019-00670-y

Uplift modeling is an instrument used to estimate the change in outcome due to a treatment at the individual entity level. Uplift models assist decision-makers in optimally allocating scarce resources. This allows the selection of the subset of entities for which the effect of a treatment will be largest and, as such, the maximization of the overall returns. The literature on uplift modeling mostly focuses on queries concerning the effect of a single treatment and rarely considers situations where more than one treatment alternative is utilized. This article surveys the current literature on multitreatment uplift modeling and proposes two novel techniques: the naive uplift approach and the multitreatment modified outcome approach. Moreover, a benchmarking experiment is performed to contrast the performances of different multitreatment uplift modeling techniques across eight data sets from various domains. We verify and, if needed, correct the imbalance among the pretreatment characteristics of the treatment groups by means of optimal propensity score matching, which ensures a correct interpretation of the estimated uplift. Conventional and recently proposed evaluation metrics are adapted to the multitreatment scenario to assess performance. None of the evaluated techniques consistently outperforms other techniques. Hence, it is concluded that performance largely depends on the context and problem characteristics. The newly proposed techniques are found to offer similar performances compared to state-of-the-art approaches.