Skip to Main content Skip to Navigation
Conference papers

A Large Scale Benchmark for Uplift Modeling

Abstract : Uplift modeling is an important yet novel area of research in machine learning which aims to explain and to estimate the causal impact of a treatment at the individual level. In the digital advertising industry, the treatment is exposure to different ads and uplift modeling is used to direct marketing efforts towards users for whom it is the most efficient [1]. To foster research in this topic we release a publicly available collection of 25 million samples from a randomized control trial, scaling up previously available datasets by a healthy 590x factor. We provide details on the data collection and sanity checks performed that allow the use of this data for counter-factual prediction. We formalize the task of uplift prediction that could be performed with this data, along with the relevant evaluation metrics. Finally we show that the dataset size makes it now possible to reach statistical significance when evaluating baseline methods on the most challenging target.
Complete list of metadatas

Cited literature [22 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-02515860
Contributor : Eustache Diemert <>
Submitted on : Monday, March 23, 2020 - 4:18:05 PM
Last modification on : Saturday, March 28, 2020 - 1:41:34 AM

File

large-scale-benchmark.pdf
Files produced by the author(s)

Identifiers

Collections

LIG | UGA

Citation

Eustache Diemert, Artem Betlei, Christophe Renaudin, Massih-Reza Amini. A Large Scale Benchmark for Uplift Modeling. KDD, 2018, London, United Kingdom. ⟨10.1145/nnnnnnn.nnnnnnn⟩. ⟨hal-02515860⟩

Share

Metrics

Record views

18

Files downloads

18