A Systematic Literature Review : Adopting Machine Learning (ML) Models to Measure the Financial Inclusion of Gig Workers in Malaysia

Abstract

The rapid expansion of the gig economy in Malaysia has created new employment opportunities but has also intensified challenges related to financial inclusion, particularly access to credit and formal lending services. This study aims to systematically review the financial barriers faced by gig workers and examine the role of Machine Learning (ML) in enhancing credit risk assessment and financial accessibility for individuals engaged in non-traditional employment. A systematic literature review was conducted following the PRISMA 2020 guidelines. Relevant studies published between 2020 and 2025 were retrieved from major open-access databases, including Google Scholar, ScienceDirect, DOAJ, SpringerOpen, MDPI, and PLOS. The selected studies were analysed using thematic synthesis to identify recurring patterns, machine learning applications, data features, and research gaps related to gig workers’ creditworthiness. The findings reveal that gig workers experience significant difficulties in obtaining credit due to irregular income streams, limited employment documentation, and insufficient credit histories. This study contributes to the literature by proposing a conceptual framework that integrates machine learning techniques with risk identification, assessment, evaluation, mitigation, and monitoring processes to support more inclusive credit risk management. The framework offers a foundation for future empirical research and policy development aimed at improving financial inclusion among gig workers in Malaysia.