Explainable artificial intelligence for digital finance and consumption upgrading

• Published in: Finance research letters Vol. 58; p. 104489
• Main Authors: Zhou, Linjiang, Shi, Xiaochuan, Bao, Yaxiong, Gao, Lihua, Ma, Chao
• Format: Journal Article
• Language: English
• Published: Elsevier Inc 01-12-2023
• Subjects: Consumption upgrading; Digital finance; Explainable artificial intelligence; Machine learning; Shapley values; Explainable artificial intelligence; Shapley values; Digital finance; Consumption upgrading; Machine learning
• ISSN: 1544-6123; 1544-6131
• DOI: 10.1016/j.frl.2023.104489

Recently, the role of digital finance in promoting consumer upgrades has become increasingly evident. By applying boosting trees and Shapley values, we proposed an explainable artificial intelligence method to obtain more effective analysis results than those obtained using linear regression models.
We studied the China Household Finance Survey data and the Digital Financial Inclusion Index of Peking University, which includes data from 34,643 and 40,013 households in 2019 and 2017, respectively. Our research shows that, the explainable artificial intelligence techniques can provide more innovative economic insights.
•We studyed the digital finance and consumption upgrading with XAI.•We demonstrated that XAI offers more meaningful and practical results.•Our findings suggested a complex non-linear influence of consumption upgrading.