Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
110 tokens/sec
GPT-4o
56 tokens/sec
Gemini 2.5 Pro Pro
44 tokens/sec
o3 Pro
6 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Learning to Infer Unobserved Behaviors: Estimating User's Preference for a Site over Other Sites (2312.16177v1)

Published 15 Dec 2023 in cs.IR, cs.LG, stat.ME, and stat.ML

Abstract: A site's recommendation system relies on knowledge of its users' preferences to offer relevant recommendations to them. These preferences are for attributes that comprise items and content shown on the site, and are estimated from the data of users' interactions with the site. Another form of users' preferences is material too, namely, users' preferences for the site over other sites, since that shows users' base level propensities to engage with the site. Estimating users' preferences for the site, however, faces major obstacles because (a) the focal site usually has no data of its users' interactions with other sites; these interactions are users' unobserved behaviors for the focal site; and (b) the Machine Learning literature in recommendation does not offer a model of this situation. Even if (b) is resolved, the problem in (a) persists since without access to data of its users' interactions with other sites, there is no ground truth for evaluation. Moreover, it is most useful when (c) users' preferences for the site can be estimated at the individual level, since the site can then personalize recommendations to individual users. We offer a method to estimate individual user's preference for a focal site, under this premise. In particular, we compute the focal site's share of a user's online engagements without any data from other sites. We show an evaluation framework for the model using only the focal site's data, allowing the site to test the model. We rely upon a Hierarchical Bayes Method and perform estimation in two different ways - Markov Chain Monte Carlo and Stochastic Gradient with Langevin Dynamics. Our results find good support for the approach to computing personalized share of engagement and for its evaluation.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (35)
  1. Greg M Allenby and Peter E Rossi. 2006. Hierarchical bayes models. The handbook of marketing research: Uses, misuses, and future advances (2006), 418–440.
  2. An Optimization-Based Approach to Discover the Unobservable Behavior of a Discrete-Event System Through Interpreted Petri Nets. IEEE Transactions on Automation Science and Engineering 17, 2 (2019), 784–798.
  3. Buy It Again: Modeling Repeat Purchase Recommendations. In Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. 62–70.
  4. Multivariate arrival times with recurrent neural networks for personalized demand forecasting. In 2018 IEEE International Conference on Data Mining Workshops (ICDMW). IEEE, 810–819.
  5. Learning to rank features for recommendation over multiple categories. In Proceedings of the 39th International ACM SIGIR conference on Research and Development in Information Retrieval. 305–314.
  6. Yuxin Chen and Joel H Steckel. 2012. Modeling credit card share of wallet: Solving the incomplete information problem. Journal of Marketing Research 49, 5 (2012).
  7. Mick P Couper. 2000. Web surveys: A review of issues and approaches. The Public Opinion Quarterly 64, 4 (2000), 464–494.
  8. Deep neural networks for youtube recommendations. In Proceedings of the 10th ACM conference on recommender systems. 191–198.
  9. Timing is everything? The effects of timing and placement of online privacy indicators. In Proceedings of the SIGCHI Conference on Human Factors in Computing Systems.
  10. A multi-view deep learning approach for cross domain user modeling in recommendation systems. In Proceedings of the 24th international conference on world wide web. 278–288.
  11. Edward Fox and Jacquelyn Thomas. 2006. A Hierarchical Bayesian Approach to Predicting Retail Customers’ Share-of-Wallet Loyalty. SMU Cox School of Business Research Paper 07-003 (2006).
  12. Şule Gündüz and M Tamer Özsu. 2003. A web page prediction model based on click-stream tree representation of user behavior. In Proceedings of the ninth ACM SIGKDD international conference on Knowledge discovery and data mining.
  13. Ruey-Shan Guo. 2009. A multi-category inter-purchase time model based on hierarchical Bayesian theory. Expert Systems with Applications 36, 3 (2009).
  14. Session-based recommendations with recurrent neural networks. arXiv preprint arXiv:1511.06939 (2015).
  15. ADVANCES IN INFORMATION RETRIEVAL: 43rd European Conference on Ir Research. Vol. 12656. Springer Nature.
  16. Web search clickstreams. In Proceedings of the 6th ACM SIGCOMM conference on Internet measurement. 245–250.
  17. Just in time recommendations: Modeling the dynamics of boredom in activity streams. In Proceedings of the Eighth ACM International Conference on Web Search and Data Mining. 233–242.
  18. A hazard based approach to user return time prediction. In Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining.
  19. Learning to rank for recommender systems. In Proceedings of the 7th ACM Conference on Recommender Systems. 493–494.
  20. Retrial queuing system with randomized push-out mechanism and non-preemptive priority. Procedia Computer Science 150 (2019), 716–725.
  21. Improving propensity score weighting using machine learning. Statistics in medicine 29, 3 (2010), 337–346.
  22. Modeling consumer visit frequency on the internet. In Proceedings of the 34th Annual Hawaii International Conference on System Sciences. IEEE, 9–pp.
  23. Hui Li and Michael Muskulus. 2007. Analysis and modeling of job arrivals in a production grid. ACM SIGMETRICS performance evaluation review 34, 4 (2007), 59–70.
  24. Stochastic gradient descent as approximate bayesian inference. arXiv preprint arXiv:1704.04289 (2017).
  25. numerator.com. 2020. Consumer panel data done with speed, scale and coverage never previously imagined. https://www.numerator.com/omnipanel-consumer-panel. [Online; accessed 3rd-May-2022].
  26. An infinite latent attribute model for network data. arXiv preprint arXiv:1206.6416 (2012).
  27. Mark A Rothstein and Stacey A Tovino. 2019. California takes the lead on data privacy law. Hastings Center Report 49, 5 (2019), 4–5.
  28. Identification of discrete event systems unobservable behaviour by petri nets using language projections. In 2015 European Control Conference (ECC). IEEE, 464–471.
  29. PB Seetharaman and Pradeep K Chintagunta. 2003. The proportional hazard model for purchase timing: A comparison of alternative specifications. Journal of Business & Economic Statistics 21, 3 (2003), 368–382.
  30. Extreme learning machine for missing data using multiple imputations. Neurocomputing 174 (2016), 220–231.
  31. When Inverse Propensity Scoring does not Work: Affine Corrections for Unbiased Learning to Rank. In Proceedings of the 29th ACM International Conference on Information & Knowledge Management. 1475–1484.
  32. Paul Voigt and Axel Von dem Bussche. 2017. The eu general data protection regulation (gdpr). A Practical Guide, 1st Ed., Cham: Springer International Publishing 10 (2017), 3152676.
  33. Max Welling and Yee W Teh. 2011. Bayesian learning via stochastic gradient Langevin dynamics. In Proceedings of the 28th international conference on machine learning (ICML-11). Citeseer, 681–688.
  34. Scalable demand-aware recommendation. In Advances in Neural Information Processing Systems. 2412–2421.
  35. A neural autoregressive approach to collaborative filtering. In International Conference on Machine Learning. PMLR, 764–773.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (5)
  1. Tanay Anand (2 papers)
  2. Paridhi Maheshwari (7 papers)
  3. A V Lakshmy (1 paper)
  4. Vishal Jain (11 papers)
  5. Atanu R Sinha (7 papers)

Summary

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

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