Towards Balanced Representation Learning for Credit Policy Evaluation

Yiyan Huang, Cheuk Hang Leung, Shumin Ma, Zhiri Yuan, Qi Wu*, Siyi Wang, Dongdong Wang, Zhixiang Huang

*Corresponding author for this work

Research output: Chapters, Conference Papers, Creative and Literary WorksRGC 32 - Refereed conference paper (with host publication)peer-review

3 Citations (Scopus)

Abstract

Credit policy evaluation presents profitable opportunities for E-commerce platforms through improved decision-making. The core of policy evaluation is estimating the causal effects of the policy on the target outcome. However, selection bias presents a key challenge in estimating causal effects from real-world data. Some recent causal inference methods attempt to mitigate selection bias by leveraging covariate balancing in the representation space to obtain the domain-invariant features. However, it is noticeable that balanced representation learning can be accompanied by a failure of domain discrimination, resulting in the loss of domain-related information. This is referred to as the over-balancing issue. In this paper, we introduce a novel objective for representation balancing methods to do policy evaluation. In particular, we construct a doubly robust loss based on the predictions of treatment and outcomes, serving as a prerequisite for covariate balancing to deal with the over-balancing issue. In addition, we investigate how to improve treatment effect estimations by exploiting the unconfoundedness assumption. The extensive experimental results on benchmark datasets and a newly introduced credit dataset show a general outperformance of our method compared with existing methods. © 2023 by the author(s)
Original languageEnglish
Title of host publicationProceedings of The 26th International Conference on Artificial Intelligence and Statistics
EditorsFrancisco Ruiz, Jennifer Dy, Jan-Willem van de Meent
PublisherPMLR
Pages3677-3692
Volume206
Publication statusPublished - Apr 2023
Event26th International Conference on Artificial Intelligence and Statistics (AISTATS 2023) - Palau de Congressos, Valencia, Spain
Duration: 25 Apr 202327 Apr 2023
http://aistats.org/aistats2023/#:~:text=The%2026th%20International%20Conference%20on,as%20an%20in%2Dperson%20event.

Publication series

NameProceedings of Machine Learning Research
ISSN (Print)2640-3498

Conference

Conference26th International Conference on Artificial Intelligence and Statistics (AISTATS 2023)
Country/TerritorySpain
CityValencia
Period25/04/2327/04/23
Internet address

Bibliographical note

Research Unit(s) information for this publication is provided by the author(s) concerned.

Funding

Qi Wu acknowledges the support from The CityU-JD Digits Joint Laboratory in Financial Technology and Engineering; The Hong Kong Research Grants Council [General Research Fund 14206117, 11219420, and 11200219]; The CityU SRG-Fd fund 7005300, and The HK Institute of Data Science. The work described in this paper was partially supported by the InnoHK initiative, The Government of the HKSAR, and the Laboratory for AI-Powered Financial Technologies.

Fingerprint

Dive into the research topics of 'Towards Balanced Representation Learning for Credit Policy Evaluation'. Together they form a unique fingerprint.

Cite this