Probing Digital Footprints and Reaching for Inherent Preferences: A Cause-Disentanglement Approach to Personalized Recommendations

References

• Adomavicius G, Bockstedt JC, Curley SP, Zhang J (2013) Do recommender systems manipulate consumer preferences? A study of anchoring effects. Inform. Systems Res. 24(4):956–975.Link, Google Scholar
• Akerlof GA (1991) Procrastination and obedience. Amer. Econom. Rev. 81(2):1–19.Google Scholar
• Athey S, Imbens GW (2019) Machine learning methods that economists should know about. Annual Rev. Econom. 11(1):685–725.Crossref, Google Scholar
• Baeza-Yates R (2018) Bias on the web. Comm. ACM 61(6):54–61.Crossref, Google Scholar
• Beatty SE, Ferrell ME (1998) Impulse buying: Modeling its precursors. J. Retailing 74(2):169–191.Crossref, Google Scholar
• Bengio Y, Deleu T, Rahaman N, Ke R, Lachapelle S, Bilaniuk O, Goyal A, Pal C (2019) A meta-transfer objective for learning to disentangle causal mechanisms. Preprint, submitted January 30, https://arxiv.org/abs/1901.10912.Google Scholar
• Bonner S, Vasile F (2018) Causal embeddings for recommendation. Proc. 12th ACM Conf. Recommender Systems (Association for Computing Machinery, New York), 104–112.Google Scholar
• Breese JS, Heckerman D, Kadie C (1998) Empirical analysis of predictive algorithms for collaborative filtering. Cooper GF, Moral S, eds. Proc. 14th Conf. Uncertainty Artificial Intelligence (Morgan Kaufmann, San Francisco), 43–52.Google Scholar
• Chen X, Li L, Pan W, Ming Z (2020b) A survey on heterogeneous one-class collaborative filtering. ACM Trans. Inform. Systems 38(4):1–54.Google Scholar
• Chen J, Dong H, Wang X, Feng F, Wang M, He X (2023) Bias and debias in recommender system: A survey and future directions. ACM Trans. Inform. Systems 41(3):1–39.Crossref, Google Scholar
• Chen C, Zhang M, Zhang Y, Ma W, Liu Y, Ma S (2020a) Efficient heterogeneous collaborative filtering without negative sampling for recommendation. Proc. AAAI Conf. Artificial Intelligence (AAAI Press, Palo Alto, CA), 19–26.Crossref, Google Scholar
• Cheng L, Guo R, Moraffah R, Sheth P, Candan KS, Liu H (2022) Evaluation methods and measures for causal learning algorithms. IEEE Trans. Artificial Intelligence 3(6):924–943.Crossref, Google Scholar
• Choi H, Mela CF, Balseiro SR, Leary A (2020) Online display advertising markets: A literature review and future directions. Inform. Systems Res. 31(2):556–575.Link, Google Scholar
• Ciampaglia GL, Nematzadeh A, Menczer F, Flammini A (2018) How algorithmic popularity bias hinders or promotes quality. Sci. Rep. 8(1):1–7.Crossref, Google Scholar
• DellaVigna S (2009) Psychology and economics: Evidence from the field. J. Econom. Literature 47(2):315–372.Crossref, Google Scholar
• Dewan S, Ho YJ, Ramaprasad J (2017) Popularity or proximity: Characterizing the nature of social influence in an online music community. Inform. Systems Res. 28(1):117–136.Link, Google Scholar
• Dhami S (2016) The Foundations of Behavioral Economic Analysis (Oxford University Press, Oxford, UK).Google Scholar
• Ding J, Yu G, He X, Quan Y, Li Y, Chua TS, Jin D, Yu J (2018) Improving implicit recommender systems with view data. Proc. 27th Internat. Joint Conf. Artificial Intelligence (AAAI Press, Palo Alto, CA), 3343–3349.Google Scholar
• Dowling K, Guhl D, Klapper D, Spann M, Stich L, Yegoryan N (2020) Behavioral biases in marketing. J. Acad. Marketing Sci. 48(3):449–477.Crossref, Google Scholar
• Fishburn PC (1970) Utility theory for decision making. Technical report, Research Analysis Corporation, McLean, VA.Google Scholar
• Fleder D, Hosanagar K (2009) Blockbuster culture’s next rise or fall: The impact of recommender systems on sales diversity. Management Sci. 55(5):697–712.Link, Google Scholar
• Gao C, He X, Gan D, Chen X, Feng F, Li Y, Chua TS, Yao L, Song Y, Jin D (2019) Learning to recommend with multiple cascading behaviors. IEEE Trans. Knowledge Data Engrg. 33(6):2588–2601.Crossref, Google Scholar
• Gregor S, Hevner AR (2013) Positioning and presenting design science research for maximum impact. MIS Quart. 37(2):337–355.Crossref, Google Scholar
• Guo R, Cheng L, Li J, Hahn PR, Liu H (2020) A survey of learning causality with data: Problems and methods. ACM Comput. Surveys 53(4):1–37.Google Scholar
• Guo H, Tang R, Ye Y, Li Z, He X (2017) DeepFM: A factorization-machine based neural network for CTR prediction. Proc. 26th Internat. Joint Conf. Artificial Intelligence (AAAI Press, Palo Alto, CA), 1725–1731.Google Scholar
• Hu N, Pavlou PA, Zhang JJ (2017) On self-selection biases in online product reviews. MIS Quart. 41(2):449–471.Crossref, Google Scholar
• Huang B, Zhang K, Zhang J, Ramsey J, Sanchez-Romero R, Glymour C, Schölkopf B (2020) Causal discovery from heterogeneous/nonstationary data. J. Machine Learn. Res. 21(1):3482–3534.Google Scholar
• Hui SK, Inman JJ, Huang Y, Suher J (2013) The effect of in-store travel distance on unplanned spending: Applications to mobile promotion strategies. J. Marketing 77(2):1–16.Crossref, Google Scholar
• Iyer GR, Blut M, Xiao SH, Grewal D (2020) Impulse buying: A meta-analytic review. J. Acad. Marketing Sci. 48(3):384–404.Crossref, Google Scholar
• Johnson CC (2014) Logistic matrix factorization for implicit feedback data. NIPS Workshop Distributed Matrix Computations (Spotify, New York).Google Scholar
• Jonas E, Schulz-Hardt S, Frey D, Thelen N (2001) Confirmation bias in sequential information search after preliminary decisions: An expansion of dissonance theoretical research on selective exposure to information. J. Personality Soc. Psych. 80(4):557–571.Crossref, Google Scholar
• Karaman H (2021) Online review solicitations reduce extremity bias in online review distributions and increase their representativeness. Management Sci. 67(7):4420–4445.Link, Google Scholar
• Koren Y, Bell R, Volinsky C (2009) Matrix factorization techniques for recommender systems. Computer 42(8):30–37.Crossref, Google Scholar
• Lam WY, Andrews B, Ramsey J (2022) Greedy relaxations of the sparsest permutation algorithm. Cussens J, Zhang K, eds. Proc. 38th Conf. Uncertainty Artificial Intelligence. Proceedings of Machine Learning Research, vol. 180 (PMLR, New York), 1052–1062.Google Scholar
• Lee L, Inman JJ, Argo JJ, Böttger T, Dholakia U, Gilbride T, Van Ittersum K, et al. (2018) From browsing to buying and beyond: The needs-adaptive shopper journey model. J. Assoc. Consumer Res. 3(3):277–293.Crossref, Google Scholar
• Li SS, Karahanna E (2015) Online recommendation systems in a B2C E-commerce context: A review and future directions. J. Assoc. Inform. Systems 16(2):72–107.Google Scholar
• Li X, Grahl J, Hinz O (2022) How do recommender systems lead to consumer purchases? A causal mediation analysis of a field experiment. Inform. Systems Res. 33(2):620–637.Link, Google Scholar
• Liang D, Charlin L, Blei DM (2016a) Causal inference for recommendation. Causation: Foundation to Application Workshop, vol. 6, No. 41 (AUAI, New York), 108.Google Scholar
• Liang D, Charlin L, McInerney J, Blei DM (2016b) Modeling user exposure in recommendation. Proc. 25th Internat. Conf. World Wide Web (International World Wide Web Conferences Steering Committee, Geneva), 951–961.Google Scholar
• Ma W, Chen GH (2019) Missing not at random in matrix completion: The effectiveness of estimating missingness probabilities under a low nuclear norm assumption. Wallach H, Larochelle H, Beygelzimer A, d’Alché-Buc F, Fox E, Garnett R, eds. Proc. 33rd Internat. Conf. Neural Inform. Processing Systems, vol. 32 (Curran Associates, Red Hook, NY), 14900–14909.Google Scholar
• Miao W, Geng Z, Tchetgen Tchetgen EJ (2018) Identifying causal effects with proxy variables of an unmeasured confounder. Biometrika 105(4):987–993.Crossref, Google Scholar
• Mnih A, Salakhutdinov RR (2007) Probabilistic matrix factorization. Platt J, Koller D, Singer Y, Roweis S, eds. Advances in Neural Information Processing Systems, vol. 20 (Curran Associates, Red Hook, NY).Google Scholar
• Montgomery MR, Gragnolati M, Burke KA, Paredes E (2000) Measuring living standards with proxy variables. Demography 37(2):155–174.Crossref, Google Scholar
• Muchnik L, Aral S, Taylor SJ (2013) Social influence bias: A randomized experiment. Science 341(6146):647–651.Crossref, Google Scholar
• Nikolov D, Lalmas M, Flammini A, Menczer F (2019) Quantifying biases in online information exposure. J. Assoc. Inform. Sci. Tech. 70(3):218–229.Crossref, Google Scholar
• Olley GS, Pakes A (1996) The dynamics of productivity in the telecommunications equipment industry. Econometrica 64(6):1263–1297.Crossref, Google Scholar
• Pearl J (2009) Causality (Cambridge University Press, Cambridge, UK).Crossref, Google Scholar
• Pearl J, Glymour M, Jewell NP (2016) Causal Inference in Statistics: A Primer (John Wiley & Sons, Hoboken, NJ).Google Scholar
• Peng J, Liang C (2023) On the differences between view-based and purchase-based recommender systems. MIS Quart. 47(2):875–900.Crossref, Google Scholar
• Sahoo N, Singh PV, Mukhopadhyay T (2012) A hidden Markov model for collaborative filtering. MIS Quart. 36(4):1329–1356.Crossref, Google Scholar
• Saito Y, Yaginuma S, Nishino Y, Sakata H, Nakata K (2020) Unbiased recommender learning from missing-not-at-random implicit feedback. Proc. 13th Internat. Conf. Web Search Data Mining (Association for Computing Machinery, New York), 501–509.Google Scholar
• Schnabel T, Swaminathan A, Singh A, Chandak N, Joachims T (2016) Recommendations as treatments: Debiasing learning and evaluation. Balcan MF, Weinberger KQ eds. Proc. 33rd Internat. Conf. Machine Learn. (JMLR.org), 1670–1679.Google Scholar
• Schölkopf B, Locatello F, Bauer S, Ke NR, Kalchbrenner N, Goyal A, Bengio Y (2021) Toward causal representation learning. Proc. IEEE 109(5):612–634.Crossref, Google Scholar
• Shipley B, Douma JC (2020) Generalized AIC and chi‐squared statistics for path models consistent with directed acyclic graphs. Ecology 101(3):e02960.Crossref, Google Scholar
• Simon HA (1955) A behavioral model of rational choice. Quart. J. Econom. 69(1):99–118.Crossref, Google Scholar
• Simonson I (2008) Will I like a “medium” pillow? Another look at constructed and inherent preferences. J. Consumer Psych. 18(3):155–169.Crossref, Google Scholar
• Sun T, Yuan Z, Li C, Zhang K, Xu J (2024) The value of personal data in Internet commerce: A high-stakes field experiment on data regulation policy. Management Sci. 70(4):2645–2660.Link, Google Scholar
• Valogianni K, Padmanabhan B, Qiu L (2023) Causal ABM: A methodology for learning plausible causal models using agent-based modeling. Preprint, submitted January 31, http://dx.doi.org/10.2139/ssrn.4343647.Google Scholar
• Wang T, Rudin C (2022) Causal rule sets for identifying subgroups with enhanced treatment effects. INFORMS J. Comput. 34(3):1626–1643.Link, Google Scholar
• Wang W, Xu J, Wang M (2018b) Effects of recommendation neutrality and sponsorship disclosure on trust vs. distrust in online recommendation agents: Moderating role of explanations for organic recommendations. Management Sci. 64(11):5198–5219.Link, Google Scholar
• Wang C, Zhang X, Hann IH (2018a) Socially nudged: A quasi-experimental study of friends’ social influence in online product ratings. Inform. Systems Res. 29(3):641–655.Link, Google Scholar
• Wang W, Feng F, He X, Wang X, Chua TS (2021b) Deconfounded recommendation for alleviating bias amplification. Proc. 27th ACM SIGKDD Conf. Knowledge Discovery Data Mining (Association for Computing Machinery, New York), 1717–1725.Google Scholar
• Wang S, Cao L, Wang Y, Sheng QZ, Orgun MA, Lian D (2021a) A survey on session-based recommender systems. ACM Comput. Surveys 54(7):1–38.Crossref, Google Scholar
• Wooldridge JM (2015) Introductory Econometrics: A Modern Approach (Cengage Learning, Boston).Google Scholar
• Xia K, Lee KZ, Bengio Y, Bareinboim E (2021) The causal-neural connection: Expressiveness, learnability, and inference. Ranzato M, Beygelzimer A, Dauphin Y, Liang PS, Vaughan JW, eds. Advances in Neural Information Processing Systems, vol. 34 (Curran Associates, Red Hook, NY), 10823–10836.Google Scholar
• Xie F, Cai R, Huang B, Glymour C, Hao Z, Zhang K (2020) Generalized independent noise condition for estimating latent variable causal graphs. Larochelle H, Ranzato M, Hadsell R, Balcan MF, Lin H, eds. Advances in Neural Information Processing Systems, vol. 33 (Curran Associates, Red Hook, NY), 14891–14902.Google Scholar
• Yadav MS, De Valck K, Hennig-Thurau T, Hoffman DL, Spann M (2013) Social commerce: A contingency framework for assessing marketing potential. J. Interactive Marketing 27(4):311–323.Crossref, Google Scholar
• Zhang Y, Feng F, He X, Wei T, Song C, Ling G, Zhang Y (2021) Causal intervention for leveraging popularity bias in recommendation. Proc. 44th Internat. ACM SIGIR Conf. Res. Development Inform. Retrieval (Association for Computing Machinery, New York), 11–20.Google Scholar
• Zheng J, Qi Z, Dou Y, Tan Y (2019) How mega is the mega? Exploring the spillover effects of WeChat using graphical model. Inform. Systems Res. 30(4):1343–1362.Link, Google Scholar
• Zheng Y, Gao C, Li X, He X, Li Y, Jin D (2021) Disentangling user interest and conformity for recommendation with causal embedding. Proc. Web Conf. 2021 (Association for Computing Machinery, New York), 2980–2991.Google Scholar
• Zhou T, Wang Y, Yan L, Tan Y (2023) Spoiled for choice? Personalized recommendation for healthcare decisions: A multiarmed bandit approach. Inform. Systems Res. 34(4):1493–1512.Link, Google Scholar