Scholarlink

Currently, a significant issue for businesses focused on banking, financial services, and insurance (BSFI) is employee turnover. Reducing employee turnover should be a top priority for businesses since departing employees take with them vital tacit knowledge that gives the organization a competitive edge. It must comprehend the root reasons for turnover in order to achieve this goal. In order to anticipate employee turnover in BSFI enterprises based on perceived job results, this study aims to uncover the dispositional qualities of BSFI managers at three separate levels, including personality, individual attributes, and demography. The study uses decision trees and artificial neural networks to find the most reliable indicators of attrition in BSFI businesses. The research finds that characteristics impacting work performance and intention to leave differ depending on the degree of the employment. Level 1 pertains to demographic age; Level 2 pertains to extraversion, resilience, intellectual humility, and self-efficacy; Level 3 pertains to emotional stability, which influences job outcomes and turnover Intention. The article presents the rules produced by the strongest predictor model and algorithm. Among other relevant methods, cross-validation, lift charts, and the Gini Index have all been used to verify the results. The study will support staff retention management, enhancing the company's overall performance.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Hybrid Machine Learning Prescriptive Framework with ANN and Decision Tree Approaches for BFSI Retention Management

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Rajit Verma,
  • Ram Singh,
  • Dibyahash Bordoloi,
  • Pradeepta Kumar Sarangi,
  • Naaz Gorowara,
  • Ved Prakash Dubey

摘要

Currently, a significant issue for businesses focused on banking, financial services, and insurance (BSFI) is employee turnover. Reducing employee turnover should be a top priority for businesses since departing employees take with them vital tacit knowledge that gives the organization a competitive edge. It must comprehend the root reasons for turnover in order to achieve this goal. In order to anticipate employee turnover in BSFI enterprises based on perceived job results, this study aims to uncover the dispositional qualities of BSFI managers at three separate levels, including personality, individual attributes, and demography. The study uses decision trees and artificial neural networks to find the most reliable indicators of attrition in BSFI businesses. The research finds that characteristics impacting work performance and intention to leave differ depending on the degree of the employment. Level 1 pertains to demographic age; Level 2 pertains to extraversion, resilience, intellectual humility, and self-efficacy; Level 3 pertains to emotional stability, which influences job outcomes and turnover Intention. The article presents the rules produced by the strongest predictor model and algorithm. Among other relevant methods, cross-validation, lift charts, and the Gini Index have all been used to verify the results. The study will support staff retention management, enhancing the company's overall performance.