A Machine Learning Model to Evaluate Digital Financial Services Adoption and Sustainable Women Empowerment

Abstract

Purpose: Financial services enabled by digital technology can help address the challenges faced by women by overcoming the barriers of proximity and cost. Despite notable advancements in digital financial inclusion in India, women still face obstacles in accessing and utilizing digital financial services.

Design/methodology/approach: A machine learning-based self-efficacy-value adoption model (SVAM) is applied to study the influence of self-efficacy and perceived value on the intention to adopt digital financial services (DFS). Likewise, a machine learning-based threshold decision theory was applied to examine the relationship between digital financial services access and the dimension of sustainable women empowerment in rural India.

Findings: The results suggest that enhancing user experience and highlighting the benefits of DFS can increase adoption rates among women, thus promoting their economic and social empowerment.

Originality/value: In this study, the authors examine an integrated framework based on supervised machine learning to access digital financial services for rural women. They are among the first to apply a self-efficacy-based value adoption model through machine learning to explore this topic. The adoption of digital financial services significantly enhances women's economic, social, and psychological empowerment in rural areas. This evidence-based study will inform policy discussions on developing a gender-sensitive strategy to promote the adoption of digital financial services among women.