Human-Centered Machine Learning Implementation in Banking: Case Study in BRILink (BRI Branchless Banking) Agent Acquisition, Upgrade, and Activation

BRILink is a branchless banking service that provides quintessential banking transactions to the unbanked population in Indonesia through human agents. Due to the important role of agents, the quantity and quality of agents become critical in BRILink operations to achieve the expected business performance. Thus, new agent acquisition as well as agent upgrade and activation are essential as endeavors to maintain and improve agent quantity and quality. However, the existing acquisition, upgrade, and activation method is troublesome due its high reliance on subjective judgment and non-data-driven approach. Therefore, human-centered machine learning solutions are implemented to determine highly qualified and potential customers to be acquired, and agents to be upgraded and activated. Based on evaluation, the implemented machine learning solutions significantly can achieve thousands of agent acquisition and up to 18% increases of agent upgrade and activation, then increase above 13% fee-based income on average.