Skip to main content
Springer Nature Link
Log in

GRFlift: uplift modeling for multi-treatment within GMV constraints

  • Published:
Applied Intelligence Aims and scope Submit manuscript

    We’re sorry, something doesn't seem to be working properly.

    Please try refreshing the page. If that doesn't work, please contact support so we can address the problem.

Abstract

As a primary goal of predictive analytics, uplift modeling is used to estimate what impact a specific action or treatment will have on an outcome. In convention, the treatment is evaluated as a success once the buyer has purchased following the treatment, regardless of the kinds of treatments and the corresponding cost. Obviously, it cannot be classified as a binary classification problem. Therefore, we extend the ordinary uplift model to support multi-treatments tasks. In order to reconcile this aspect of interpretability with tree-based models, we use random forest (RF) as our base model. We present Gross Merchandise Value (GMV)-based RF for uplift modeling (GRFlift): an uplift model, where typical commercial evaluation GMV is designed as novel tree splitting criteria to directly quantify the uplift achievement. A targeted regularization term is also designed to adjust the splitting distribution differences. The splitting process proposed in the model achieves the goal of maximizing profit while showing the optimal treatment assignment. The performance of our method is confirmed by the industrial data, synthetic data, and observation data. Consequently, distributing different moderate treatments to different users can achieve obvious attraction and avoid unnecessary investment.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5

Similar content being viewed by others

Explore related subjects

Discover the latest articles, news and stories from top researchers in related subjects.

References

  1. Angrist J, Imbens G (1995) Identification and estimation of local average treatment effects. In: Social science electronic publishing

  2. Austin P C (2011) An introduction to propensity score methods for reducing the effects of confounding in observational studies. Multivar Behav Res 46(3):399–424

    Article  Google Scholar 

  3. Chickering D M, Heckerman D (2000) A decision theoretic approach to targeted advertising. In: Proceedings of the sixteenth conference on uncertainty in artificial intelligence, pp 82–88

  4. Correa J, Bareinboim E (2020) A calculus for stochastic interventions: causal effect identification and surrogate experiments. In: AAAI 34(06), pp 10093–10100

  5. Debaere S, Devriendt F, Brunneder J et al (2019) Reducing inferior member community participation using uplift modeling: evidence from a field experiment. Decis Support Syst 123:113–117

    Article  Google Scholar 

  6. Devriendt F, Moldovan D, Verbeke W (2018) A literature survey and experimental evaluation of the state-of-the-art in uplift modeling: a stepping stone toward the development of prescriptive analytics. Big Data 6(1):13–41

    Article  Google Scholar 

  7. Diemert E, Betlei A, Renaudin C et al (2018) A large scale benchmark for uplift modeling. In: KDD

  8. Gubela R M, Lessmann S (2021) Uplift modeling with value-driven evaluation metrics. In: Decision support systems

  9. Gubela R, Bequé A, Lessmann S et al (2019) Conversion uplift in e-commerce: a systematic benchmark of modeling strategies. Int J Inf Technol Decis Mak 18(3):747–791

    Article  Google Scholar 

  10. Hansotia B, Rukstales B (2002) Incremental value modeling. J Interact Mark 16(3):35

    Article  Google Scholar 

  11. Kim S, Mun B M, Bae S J (2018) Data depth based support vector machines for predicting corporate bankruptcy. Appl Intell 48(3):791–804

    Article  Google Scholar 

  12. Koopman R, Wang Z, Wei S J (2014) Tracing value-added and double counting in gross exports. Am Econ Rev 104(2):459–494

    Article  Google Scholar 

  13. Lin A, Merchant A, Sarkar S K et al (2019) Universal causal evaluation engine: an API for empirically evaluating causal inference models. In: ACM SIGKDD workshop on causal discovery, pp 50–58

  14. Louizos C, Shalit U, Mooij J M et al (2017) Causal effect inference with deep latent-variable models. In: NIPS, pp 25–25

  15. Luo G, Zhao B, Du S (2019) Causal inference and Bayesian network structure learning from nominal data. Appl Intell 49(1):253–264

    Article  Google Scholar 

  16. Nassif H, Kuusisto F, Burnside E S et al (2013) Uplift modeling with ROC: an SRL case study. In: ILP, pp 40–45

  17. Nie X, Wager S (2021) Quasi-oracle estimation of heterogeneous treatment effects. Biometrika 108(2):299–319

    Article  MATH  Google Scholar 

  18. Maldonado S, Miranda J, Olaya D et al (2021) Redefining profit metrics for boosting student retention in higher education. In: Decision support systems

  19. Olaya D, Vásquez J, Maldonado S et al (2020) Uplift modeling for preventing student dropout in higher education. In: Decision support systems

  20. Olaya D, Coussement K, Verbeke W (2020) A survey and benchmarking study of multitreatment uplift modeling. Data Min Knowl Discov 34(2):273–308

    Article  Google Scholar 

  21. Olaya D, Verbeke W, Van Belle J et al (2021) To do or not to do: cost-sensitive causal decision-making. arXiv:2101.01407

  22. Pingault J B, O’reilly P F, Schoeler T et al (2018) Using genetic data to strengthen causal inference in observational research. Nat Rev Genet 19(9):566–580

    Article  Google Scholar 

  23. Radcliffe N J, Surry P D (2012) Real-world uplift modelling with significance-based uplift trees. Stoch Solutions 1–33

  24. Rosenbaum P R, Rubin D B (1983) The central role of the propensity score in observational studies for causal effects. Biometrika 70(1):41–55

    Article  MATH  Google Scholar 

  25. Rubin D B (1974) Estimating causal effects of treatments in randomized and nonrandomized studies. J Educ Psychol 66(5):688–688

    Article  Google Scholar 

  26. Rzepakowski P, Jaroszewicz S (2010) Decision trees for uplift modeling. In: ICDM, pp 441–450

  27. Rzepakowski P, Jaroszewicz S (2012) Decision trees for uplift modeling with single and multiple treatments. Knowl Inf Syst 32(2):303–327

    Article  Google Scholar 

  28. Shi C, Blei D, Veitch V (2019) Adapting neural networks for the estimation of treatment effects. In: Advances in neural information processing systems, vol 32, pp 2507–2517

  29. Sołtys M, Jaroszewicz S, Rzepakowski P (2015) Ensemble methods for uplift modeling. Data Min Knowl Disc 29(6):1531–1559

    Article  Google Scholar 

  30. Verbeke W, Olaya D, Berrevoets J et al (2020) The foundations of cost-sensitive causal classification. arXiv:2007.12582

  31. Yao L, Li S, Li Y et al (2018) Representation learning for treatment effect estimation from observational data. In: Advances in neural information processing systems, p 31

  32. Zhao Y, Fang X, Simchi D (2017) Uplift modeling with multiple treatments and general response types. In: ICDM, pp 588–596

  33. Zhao Y, Fang X, Simchi D (2017) A practically competitive and provably consistent algorithm for uplift modeling. In: ICDM, pp 1171–1176

  34. Zhang Z, Kim H J, Lonjon G et al (2019) Balance diagnostics after propensity score matching. Ann Transl Med 7(1):16–16

    Article  Google Scholar 

  35. Zhao Z, Harinen T (2019) Uplift modeling for multiple treatments with cost optimization. In: DSAA, pp 422–431

Download references

Acknowledgments

This work was supported by the Xianyang Key R&D Program under Grant No. S2021ZDYF-SF-0739.

Author information

Authors and Affiliations

  1. Department of Computer Science and Technology, Tongji University, Shanghai, 201804, China

    Jun Yang & Maoyu Mao

  2. Hello Inc., Shanghai, 201199, China

    Wei Wang, Yanshen Dong, Xin He, Li Jia & Huan Chen

Authors
  1. Jun Yang
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Wei Wang
    View author publications

    You can also search for this author inPubMed Google Scholar

  3. Yanshen Dong
    View author publications

    You can also search for this author inPubMed Google Scholar

  4. Xin He
    View author publications

    You can also search for this author inPubMed Google Scholar

  5. Li Jia
    View author publications

    You can also search for this author inPubMed Google Scholar

  6. Huan Chen
    View author publications

    You can also search for this author inPubMed Google Scholar

  7. Maoyu Mao
    View author publications

    You can also search for this author inPubMed Google Scholar

Corresponding author

Correspondence to Maoyu Mao.

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Yang, J., Wang, W., Dong, Y. et al. GRFlift: uplift modeling for multi-treatment within GMV constraints. Appl Intell 53, 4827–4840 (2023). https://doi.org/10.1007/s10489-022-03769-w

Download citation

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10489-022-03769-w

Keywords