Doing More with Less: Overcoming Ineffective Long-Term Targeting Using Short-Term Signals

References

• Ascarza E (2018) Retention futility: Targeting high-risk customers might be ineffective. J. Marketing Res. 55(1):80–98.Crossref, Google Scholar
• Ascarza E, Netzer O, Hardie BG (2018b) Some customers would rather leave without saying goodbye. Marketing Sci. 37(1):54–77.Link, Google Scholar
• Ascarza E, Neslin SA, Netzer O, Anderson Z, Fader PS, Gupta S, Hardie BG, et al. (2018a) In pursuit of enhanced customer retention management: Review, key issues, and future directions. Customer Needs Solutions 5:65–81.Crossref, Google Scholar
• Athey S (2017) Beyond prediction: Using big data for policy problems. Science 355(6324):483–485.Crossref, Google Scholar
• Athey S, Wager S (2019) Estimating treatment effects with causal forests: An application. Observational Stud. 5(2):37–51.Crossref, Google Scholar
• Athey S, Wager S (2021) Policy learning with observational data. Econometrica 89(1):133–161.Crossref, Google Scholar
• Athey S, Tibshirani J, Wager S (2019b) Generalized random forests. Ann. Statist. 47(2):1148–1178.Crossref, Google Scholar
• Athey S, Chetty R, Imbens GW, Kang H (2019a) The surrogate index: Combining short-term proxies to estimate long-term treatment effects more rapidly and precisely. Technical report, National Bureau of Economic Research, Cambridge, MA.Google Scholar
• Bachmann P, Meierer M, Näf J (2021) The role of time-varying contextual factors in latent attrition models for customer base analysis. Marketing Sci. 40(4):783–809.Link, Google Scholar
• Bawa K (1990) Modeling inertia and variety seeking tendencies in brand choice behavior. Marketing Sci. 9(3):263–278.Link, Google Scholar
• Brown BW (1983) The identification problem in systems nonlinear in the variables. Econometrica 51(1):175–196.Google Scholar
• Chen H, Harinen T, Lee JY, Yung M, Zhao Z (2020) CausalML: Python package for causalmachine learning. Preprint, submitted 25, https://arxiv.org/abs/2002.11631.Google Scholar
• Chernozhukov V, Imbens GW, Newey WK (2007) Instrumental variable estimation of nonseparable models. J. Econometrics 139(1):4–14.Crossref, Google Scholar
• Chernozhukov V, Demirer M, Duflo E, Fernandez-Val I (2018) Generic machine learning inference on heterogeneous treatment effects in randomized experiments, with an application to immunization in India. Technical report, National Bureau of Economic Research, Cambridge, MA.Google Scholar
• Chesher A (2003) Identification in nonseparable models. Econometrica 71(5):1405–1441.Crossref, Google Scholar
• Deng A, Xu Y, Kohavi R, Walker T (2013) Improving the sensitivity of online controlled experiments by utilizing pre-experiment data. Proc. 6th ACM Internat. Conf. Web Search Data Mining (WSDM ’13) (Association for Computing Machinery, New York), 123–132.Google Scholar
• Dubé JP, Hitsch GJ, Rossi PE (2010) State dependence and alternative explanations for consumer inertia. RAND J. Econom. 41(3):417–445.Crossref, Google Scholar
• Dubé JP, Fang Z, Fong N, Luo X (2017) Competitive price targeting with smartphone coupons. Marketing Sci. 36(6):944–975.Link, Google Scholar
• Ellickson PB, Kar W, Reeder JC (2022) Estimating marketing component effects: Double machine learning from targeted digital promotions. Marketing Sci. 42(4):704–728.Google Scholar
• Erdem T, Keane MP (1996) Decision-making under uncertainty: Capturing dynamic brand choice processes in turbulent consumer goods markets. Marketing Sci. 15(1):1–20.Link, Google Scholar
• Fader PS, Hardie BGS (2007) Incorporating time-invariant covariates into the Pareto/NBD and BG/NBD models, http://www.brucehardie.com/notes/019.Google Scholar
• Fader PS, Hardie BG (2010) Customer-base valuation in a contractual setting: The perils of ignoring heterogeneity. Marketing Sci. 29(1):85–93.Link, Google Scholar
• Fader PS, Lattin JM (1993) Accounting for heterogeneity and nonstationarity in a cross-sectional model of consumer purchase behavior. Marketing Sci. 12(3):304–317.Link, Google Scholar
• Fader PS, Hardie BG, Lee KL (2005) “Counting your customers” the easy way: An alternative to the Pareto/NBD model. Marketing Sci. 24(2):275–284.Link, Google Scholar
• Fader PS, Hardie BG, Shang J (2010) Customer-base analysis in a discrete-time noncontractual setting. Marketing Sci. 29(6):1086–1108.Link, Google Scholar
• Gonul F, Srinivasan K (1993) Modeling multiple sources of heterogeneity in multinomial logit models: Methodological and managerial issues. Marketing Sci. 12(3):213–229.Link, Google Scholar
• Grimmer J, Messing S, Westwood SJ (2017) Estimating heterogeneous treatment effects and the effects of heterogeneous treatments with ensemble methods. Political Anal. 25(4):413–434.Crossref, Google Scholar
• Guadagni PM, Little JD (1983) A logit model of brand choice calibrated on scanner data. Marketing Sci. 2(3):203–238.Link, Google Scholar
• Gubela RM, Lessmann S, Haupt J, Baumann A, Radmer T, Gebert F (2017) Revenue uplift modeling. Machine Learning for Marketing Decision Support.Google Scholar
• Guelman L, Guillén M, Pérez-Marín AM (2012) Random forests for uplift modeling: An insurance customer retention case. Engemann KJ, Gil-Lafuente AM, Merigó JM, eds. Modeling and Simulation in Engineering, Economics and Management, MS 2012: Lecture Notes in Business Information Processing, vol. 115 (Springer, Berlin, Heidelberg), 123–133.Google Scholar
• Guelman L, Guillén M, Pérez-Marín AM (2015) Uplift random forests. Cybernetic Systems 46(3–4):230–248.Crossref, Google Scholar
• Guo Y, Coey D, Konutgan M, Li W, Schoener C, Goldman M (2021) Machine learning for variance reduction in online experiments. Adv. Neural Inform. Processing Systems 34:8637–8648.Google Scholar
• Han L, Wang X, Cai T (2021) On the evaluation of surrogate markers in real world data settings. Preprint, submitted April 12, 2021, https://arxiv.org/abs/2104.05513.Google Scholar
• Hastie T, Tibshirani R, Friedman JH, Friedman JH (2009) The Elements of Statistical Learning: Data Mining, Inference, and Prediction, vol. 2 (Springer, Berlin).Crossref, Google Scholar
• Hitsch GJ, Misra S, Walter Z (2023) Heterogeneous treatment effects and optimal targeting policy evaluation. Preprint, submitted November 6, https://dx.doi.org/10.2139/ssrn.3111957.Google Scholar
• Hoderlein S, Mammen E (2007) Identification of marginal effects in nonseparable models without monotonicity. Econometrica 75(5):1513–1518.Crossref, Google Scholar
• Hoderlein S, Mammen E (2009) Identification and estimation of local average derivatives in non-separable models without monotonicity. Econom. J. 12(1):1–25.Crossref, Google Scholar
• Horvitz DG, Thompson DJ (1952) A generalization of sampling without replacement from a finite universe. J. Amer. Statist. Assoc. 47(260):663–685.Crossref, Google Scholar
• Huang TW, Ascarza E (2023) Debiasing treatment effect estimation for privacy-protected data: A model audition and calibration approach. Preprint, September 18, https://dx.doi.org/10.2139/ssrn.4575240.Google Scholar
• Imai K, Ratkovic M (2013) Estimating treatment effect heterogeneity in randomized program evaluation. Ann. Appl. Statist. 7(1):443–470.Crossref, Google Scholar
• Imai K, Strauss A (2011) Estimation of heterogeneous treatment effects from randomized experiments, with application to the optimal planning of the get-out-the-vote campaign. Political Anal. 19(1):1–19.Crossref, Google Scholar
• Imbens GW, Newey WK (2009) Identification and estimation of triangular simultaneous equations models without additivity. Econometrica 77(5):1481–1512.Crossref, Google Scholar
• Imbens GW, Rubin DB (2015) Causal Inference in Statistics, Social, and Biomedical Sciences (Cambridge University Press, Cambridge, UK).Crossref, Google Scholar
• Imbens G, Kallus N, Mao X, Wang Y (2022) Long-term causal inference under persistent confounding via data combination. Preprint, submitted February 15, https://arxiv.org/abs/2202.07234.Google Scholar
• Jin Y, Ba S (2023) Toward optimal variance reduction in online controlled experiments. Technometrics 65(2):231–242.Google Scholar
• Jones JM, Landwehr JT (1988) Removing heterogeneity bias from logit model estimation. Marketing Sci. 7(1):41–59.Link, Google Scholar
• Keane MP (1997) Modeling heterogeneity and state dependence in consumer choice behavior. J. Bus. Econom. Statist. 15(3):310–327.Crossref, Google Scholar
• Kennedy EH (2023) Toward optimal doubly robust estimation of heterogeneous causal effects. Electronic J. Statist. 17(2):3008–3049.Crossref, Google Scholar
• Kitagawa T, Tetenov A (2018) Who should be treated? Empirical welfare maximization methods for treatment choice. Econometrica 86(2):591–616.Crossref, Google Scholar
• Künzel SR, Sekhon JS, Bickel PJ, Yu B (2019) Metalearners for estimating heterogeneous treatment effects using machine learning. Proc. Natl. Acad. Sci. USA 116(10):4156–4165.Crossref, Google Scholar
• Lemmens A, Gupta S (2020) Managing churn to maximize profits. Marketing Sci. 39(5):956–973.Link, Google Scholar
• Manski CF (2004) Statistical treatment rules for heterogeneous populations. Econometrica 72(4):1221–1246.Crossref, Google Scholar
• Mazoure B, Mineiro P, Srinath P, Sedeh RS, Precup D, Swaminathan A (2021) Improving long-term metrics in recommendation systems using short-horizon reinforcement learning. Preprint, submitted June 1, https://arxiv.org/abs/2106.00589.Google Scholar
• Mbakop E, Tabord-Meehan M (2021) Model selection for treatment choice: Penalized welfare maximization. Econometrica 89(2):825–848.Crossref, Google Scholar
• Miratrix LW, Wager S, Zubizarreta JR (2018) Shape-constrained partial identification of a population mean under unknown probabilities of sample selection. Biometrika 105(1):103–114.Crossref, Google Scholar
• Neslin SA, Gupta S, Kamakura W, Lu J, Mason CH (2006) Defection detection: Measuring and understanding the predictive accuracy of customer churn models. J. Marketing Res. 43(2):204–211.Crossref, Google Scholar
• Newey WK, Robins JR (2018) Cross-fitting and fast remainder rates for semiparametric estimation. Preprint, submitted January 27, https://arxiv.org/abs/1801.09138.Google Scholar
• Nie X, Wager S (2021) Quasi-oracle estimation of heterogeneous treatment effects. Biometrika 108(2):299–319.Crossref, Google Scholar
• Oprescu M, Syrgkanis V, Battocchi K, Hei M, Lewis G (2019) EconML: A Python package for ML-based heterogeneous treatment effects estimation. https://github.com/py-why/EconML.Google Scholar
• Padilla N, Ascarza E, Netzer O (2023) The customer journey as a source of information. Preprint, submitted November 21, http://dx.doi.org/10.2139/ssrn.4612478.Google Scholar
• Prentice RL (1989) Surrogate endpoints in clinical trials: Definition and operational criteria. Statist. Medicine 8(4):431–440.Crossref, Google Scholar
• Qian T, Yoo H, Klasnja P, Almirall D, Murphy SA (2021) Estimating time-varying causal excursion effects in mobile health with binary outcomes. Biometrika 108(3):507–527.Crossref, Google Scholar
• Roehrig CS (1988) Conditions for identification in nonparametric and parametric models. Econometrica 56(2):433–447.Crossref, Google Scholar
• Roy R, Chintagunta PK, Haldar S (1996) A framework for investigating habits, “the hand of the past,” and heterogeneity in dynamic brand choice. Marketing Sci. 15(3):280–299.Link, Google Scholar
• Rubin DB (1974) Estimating causal effects of treatments in randomized and nonrandomized studies. J. Ed. Psych. 66(5):688.Crossref, Google Scholar
• Sahoo R, Lei L, Wager S (2022) Learning from a biased sample. Preprint, submitted September 5, https://arxiv.org/abs/2209.01754.Google Scholar
• Schmittlein DC, Morrison DG, Colombo R (1987) Counting your customers: Who-are they and what will they do next? Management Sci. 33(1):1–24.Link, Google Scholar
• Seetharaman P (2004) Modeling multiple sources of state dependence in random utility models: A distributed lag approach. Marketing Sci. 23(2):263–271.Link, Google Scholar
• Simester D, Timoshenko A, Zoumpoulis SI (2020) Targeting prospective customers: Robustness of machine-learning methods to typical data challenges. Management Sci. 66(6):2495–2522.Link, Google Scholar
• Simester D, Timoshenko A, Zoumpoulis SI (2022) A sample size calculation for training and certifying targeting policies. Preprint, submitted October 06, https://dx.doi.org/10.2139/ssrn.4228297.Google Scholar
• Su L, Ura T, Zhang Y (2019) Non-separable models with high-dimensional data. J. Econometrics 212(2):646–677.Crossref, Google Scholar
• Tulin E, Susumu I, Keane Michael P (2002) A model of consumer brand and quantity choice dynamics under price uncertainty. Quant. Marketing Econom. 1:5–64.Google Scholar
• Wager S, Athey S (2018) Estimation and inference of heterogeneous treatment effects using random forests. J. Amer. Statist. Assoc. 113(523):1228–1242.Crossref, Google Scholar
• Wang Y, Sharma M, Xu C, Badam S, Sun Q, Richardson L, Chung L, et al. (2022) Surrogate for long-term user experience in recommender systems. Proc. 28th ACM SIGKDD Conf. Knowledge Discovery Data Mining (KDD ’22) (Association for Computing Machinery, New York), 4100–4109.Google Scholar
• Yadlowsky S, Fleming S, Shah N, Brunskill E, Wager S (2021) Evaluating treatment prioritization rules via rank-weighted average treatment effects. Preprint, submitted November 15, https://arxiv.org/abs/2111.07966.Google Scholar
• Yang J, Eckles D, Dhillon P, Aral S (2023) Targeting for long-term outcomes. Management Sci.Link, Google Scholar
• Yoganarasimhan H, Barzegary E, Pani A (2023) Design and evaluation of optimal free trials. Management Sci. 69(6):3220–3240.Link, Google Scholar