Counterfactual Techniques for Enhancing Customer Retention
Keywords: Counterfactual Explanations, BERT, e-commerce
Abstract: In this paper, we introduce a novel counterfactual reasoning method using eBERT embeddings to convert customers from an e-commerce company who frequently add items to their cart but don’t proceed to checkout. We demonstrate that our method i) outperforms existing techniques such as DiCE, GANs, and CFRL in key metrics such as coverage, while also maintaining a low latency; ii) balances high coverage and low latency by adjusting the number of nearest unlike neighbors, highlighting a trade-off between these competing goals; and iii) allows customization of mutable features, improving the practical applicability of our counterfactual explanations.
Primary Area: causal reasoning
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.
Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 4954
Loading