Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
184 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

A predict-and-optimize approach to profit-driven churn prevention (2310.07047v2)

Published 10 Oct 2023 in cs.LG

Abstract: In this paper, we introduce a novel predict-and-optimize method for profit-driven churn prevention. We frame the task of targeting customers for a retention campaign as a regret minimization problem. The main objective is to leverage individual customer lifetime values (CLVs) to ensure that only the most valuable customers are targeted. In contrast, many profit-driven strategies focus on churn probabilities while considering average CLVs. This often results in significant information loss due to data aggregation. Our proposed model aligns with the guidelines of Predict-and-Optimize (PnO) frameworks and can be efficiently solved using stochastic gradient descent methods. Results from 12 churn prediction datasets underscore the effectiveness of our approach, which achieves the best average performance compared to other well-established strategies in terms of average profit.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (34)
  1. S. Maldonado, G. Domínguez, D. Olaya, and W. Verbeke, “Profit-driven churn prediction for the mutual fund industry: a multisegment approach,” Omega, vol. 100, p. 102380, 2021.
  2. N. R. Tungare and A. Jain, “Net promoter score (nps) framework for improving customer loyalty in supermarket,” The Online Journal of Distance Education and e-Learning, vol. 11, no. 2, 2023.
  3. S. W. Fujo, S. Subramanian, M. A. Khder et al., “Customer churn prediction in telecommunication industry using deep learning,” Information Sciences Letters, vol. 11, no. 1, p. 24, 2022.
  4. S. Neslin, S. Gupta, W. Kamakura, J. Lu, and C. Mason, “Defection detection: Measuring and understanding the predictive accuracy of customer churn models,” Journal of Marketing Research, vol. 43, no. 2, pp. 204–211, 2006.
  5. T. Verbraken, W. Verbeke, and B. Baesens, “A novel profit maximizing metric for measuring classification performance of customer churn prediction models,” IEEE transactions on knowledge and data engineering, vol. 25, no. 5, pp. 961–973, 2012.
  6. S. Maldonado, J. Miranda, D. Olaya, J. Vásquez, and W. Verbeke, “Redefining profit metrics for boosting student retention in higher education,” Decision Support Systems, vol. 143, p. 113493, 2021.
  7. F. Devriendt, J. Berrevoets, and W. Verbeke, “Why you should stop predicting customer churn and start using uplift models,” Information Sciences, vol. 548, pp. 497–515, 2021.
  8. J. López and S. Maldonado, “Profit-based credit scoring based on robust optimization and feature selection,” Information Sciences, vol. 500, pp. 190–202, 2019.
  9. S. Maldonado, J. López, and C. Vairetti, “Profit-based churn prediction based on minimax probability machines,” European Journal of Operational Research, vol. 284, no. 1, pp. 273–284, 2020.
  10. E. Stripling, S. vanden Broucke, K. Antonio, B. Baesens, and M. Snoeck, “Profit maximizing logistic model for customer churn prediction using genetic algorithms,” Swarm and Evolutionary Computation, vol. 40, pp. 116–130, 2018.
  11. M. Óskardóttir, B. Baesens, and J. Vanthienen, “Profit based model selection for customer retention using individual customer lifetime values,” Big Data, vol. 6, no. 1, pp. 53–65, 2018.
  12. T. Vanderschueren, T. Verdonck, B. Baesens, and W. Verbeke, “Predict-then-optimize or predict-and-optimize? an empirical evaluation of cost-sensitive learning strategies,” Information Sciences, vol. 594, pp. 400–415, 2022.
  13. A. N. Elmachtoub and P. Grigas, “Smart “predict, then optimize”,” Management Science, vol. 68, no. 1, pp. 9–26, 2022.
  14. A. K. Ahmad, A. Jafar, and K. Aljoumaa, “Customer churn prediction in telecom using machine learning in big data platform,” Journal of Big Data, vol. 6, no. 1, pp. 1–24, 2019.
  15. W. Verbeke, K. Dejaeger, D. Martens, J. Hur, and B. Baesens, “New insights into churn prediction in the telecommunication sector: A profit driven data mining approach,” European Journal of Operational Research, vol. 218, no. 1, pp. 211–229, 2012.
  16. J. Mandi, J. Kotary, S. Berden, M. Mulamba, V. Bucarey, T. Guns, and F. Fioretto, “Decision-focused learning: Foundations, state of the art, benchmark and future opportunities,” 2023.
  17. A. Agrawal, B. Amos, S. Barratt, S. Boyd, S. Diamond, and J. Z. Kolter, “Differentiable convex optimization layers,” Advances in neural information processing systems, vol. 32, 2019.
  18. B. Amos and J. Z. Kolter, “Optnet: Differentiable optimization as a layer in neural networks,” in International Conference on Machine Learning.   PMLR, 2017, pp. 136–145.
  19. M. Blondel, O. Teboul, Q. Berthet, and J. Djolonga, “Fast differentiable sorting and ranking,” in International Conference on Machine Learning.   PMLR, 2020, pp. 950–959.
  20. J. Mandi and T. Guns, “Interior point solving for lp-based prediction+ optimisation,” Advances in Neural Information Processing Systems, vol. 33, pp. 7272–7282, 2020.
  21. B. Wilder, B. Dilkina, and M. Tambe, “Melding the data-decisions pipeline: Decision-focused learning for combinatorial optimization,” in Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, 2019, pp. 1658–1665.
  22. M. V. Pogančić, A. Paulus, V. Musil, G. Martius, and M. Rolinek, “Differentiation of blackbox combinatorial solvers,” in International Conference on Learning Representations, 2019.
  23. S. S. Sahoo, A. Paulus, M. Vlastelica, V. Musil, V. Kuleshov, and G. Martius, “Backpropagation through combinatorial algorithms: Identity with projection works,” in The Eleventh International Conference on Learning Representations, 2022.
  24. J. Mandi, V. Bucarey, M. M. K. Tchomba, and T. Guns, “Decision-focused learning: through the lens of learning to rank,” in International Conference on Machine Learning.   PMLR, 2022, pp. 14 935–14 947.
  25. M. Mulamba, J. Mandi, M. Diligenti, M. Lombardi, V. B. Lopez, and T. Guns, “Contrastive losses and solution caching for predict-and-optimize,” in 30th International Joint Conference on Artificial Intelligence (IJCAI-21): IJCAI-21.   International Joint Conferences on Artificial Intelligence, 2021, pp. 2833–2840.
  26. A. N. Elmachtoub, J. C. N. Liang, and R. McNellis, “Decision trees for decision-making under the predict-then-optimize framework,” in International Conference on Machine Learning.   PMLR, 2020, pp. 2858–2867.
  27. S. R. Dubey, S. K. Singh, and B. B. Chaudhuri, “Activation functions in deep learning: A comprehensive survey and benchmark,” Neurocomputing, vol. 503, pp. 92–108, 2022.
  28. K. He, X. Zhang, S. Ren, and J. Sun, “Delving deep into rectifiers: Surpassing human-level performance on imagenet classification,” in 2015 IEEE International Conference on Computer Vision (ICCV), 2015, pp. 1026–1034.
  29. G. Mena, K. Coussement, K. W. De Bock, A. De Caigny, and S. Lessmann, “Exploiting time-varying rfm measures for customer churn prediction with deep neural networks,” Annals of Operations Research, pp. 1–23, 2023.
  30. S. Sun, Z. Cao, H. Zhu, and J. Zhao, “A survey of optimization methods from a machine learning perspective,” IEEE transactions on cybernetics, vol. 50, no. 8, pp. 3668–3681, 2019.
  31. A. C. Bahnsen, D. Aouada, and B. Ottersten, “Example-dependent cost-sensitive logistic regression for credit scoring,” in 2014 13th International Conference on Machine Learning and Applications, 2014, pp. 263–269.
  32. S. Höppner, B. Baesens, W. Verbeke, and T. Verdonck, “Instance-dependent cost-sensitive learning for detecting transfer fraud,” European Journal of Operational Research, vol. 297, no. 1, pp. 291–300, 2022.
  33. N. V. Chawla, K. W. Bowyer, L. O. Hall, and W. P. Kegelmeyer, “Smote: synthetic minority over-sampling technique,” Journal of artificial intelligence research, vol. 16, pp. 321–357, 2002.
  34. J. Demšar, “Statistical comparisons of classifiers over multiple data set,” Journal of Machine Learning Research, vol. 7, pp. 1–30, 2006.

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now