Uplift Modeling with Multiple Treatments and General Response Types

@article{Zhao2017UpliftMW,
  title={Uplift Modeling with Multiple Treatments and General Response Types},
  author={Y. Zhao and X. Fang and D. Simchi-Levi},
  journal={ArXiv},
  year={2017},
  volume={abs/1705.08492}
}
  • Y. Zhao, X. Fang, D. Simchi-Levi
  • Published 2017
  • Computer Science
  • ArXiv
  • Randomized experiments have been used to assist decision-making in many areas. [...] Key Method The trees are built with a splitting criterion designed to directly optimize their uplift performance based on the proposed evaluation method. Both the evaluation method and the algorithm apply to arbitrary number of treatments and general response types. Experimental results on synthetic data and industry-provided data show that our algorithm leads to significant performance improvement over other applicable methods…Expand Abstract

    Figures and Topics from this paper.

    A Practically Competitive and Provably Consistent Algorithm for Uplift Modeling
    • 9
    • PDF
    Uplift Modeling for Multiple Treatments with Cost Optimization
    • 5
    • Highly Influenced
    • PDF
    A comparison of methods for model selection when estimating individual treatment effects
    • 13
    • PDF
    A survey and benchmarking study of multitreatment uplift modeling
    • 1
    • Highly Influenced
    • PDF
    Cost-Effective and Stable Policy Optimization Algorithm for Uplift Modeling with Multiple Treatments
    • 1
    • Highly Influenced
    • PDF
    A Policy Gradient Method with Variance Reduction for Uplift Modeling
    • 1
    • Highly Influenced
    • PDF
    Reinforcement Learning for Uplift Modeling
    • 3
    • Highly Influenced
    Learning to rank for uplift modeling
    • 1
    • PDF
    Feature Selection Methods for Uplift Modeling
    General-purpose validation and model selection when estimating individual treatment effects
    • 1
    • Highly Influenced

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 23 REFERENCES
    Decision trees for uplift modeling with single and multiple treatments
    • 94
    • PDF
    Ensemble methods for uplift modeling
    • 48
    • PDF
    Random Forests
    • 47,146
    • Highly Influential
    • PDF
    Support Vector Machines for Uplift Modeling
    • 32
    • PDF
    Decision Trees for Uplift Modeling
    • 39
    • Highly Influential
    • PDF
    Using control groups to target on predicted lift: Building and assessing uplift model
    • 49
    Real-World Uplift Modelling with Significance-Based Uplift Trees
    • 85
    • PDF