Identification, Assessment and Optimisation of Key Impact Variables in People Analytics Using AI

Abstract

Background: Human resource management (HRM) is the tactical method for a business enterprise’s optimistic and systemic administration. This study aims to identify the common and major triggering attributes and the knowledge gap between HRM and an organisation’s employee attrition rate.

Method: The employee Attrition Case Study Dataset used is an anecdotal data set that tries to figure out relevant variables that determine employee behavioural aspects towards attrition. This study investigates why attrition occurs, the major triggering attributes for employee turnover, and how it might be anticipated to employ artificial intelligence (AI) to avert corporate losses.

Results: Employees’ monthly income, age, average monthly hours, distance from home, total working years, years at the company, per cent of salary hike, number of companies worked, stock options level, job role and other factors are taken into consideration. A feature importance extraction framework was devised to investigate the various dormant factors. The findings also show feasible hypotheses that help enhance employee engagement, reinvent the worker dynamic, and higher levels of risk decrease attrition rate.

Implications: Employees’ monthly income, age, average monthly hours, distance from home, etc., are all major variables in employee attrition in the Indian IT business. This research adds to the theory development of behavioural elements in people analytics based on AI.

Purpose: Can we predict employee attrition through employee behavioural patterns advancement using AI tools.

Citation

Kameswari, J., Palivela, H., Settur, S. and Solanki, P. (2023), "Identification, Assessment and Optimisation of Key Impact Variables in People Analytics Using AI", Tyagi, P., Chilamkurti, N., Grima, S., Sood, K. and Balusamy, B. (Ed.) The Adoption and Effect of Artificial Intelligence on Human Resources Management, Part A (Emerald Studies in Finance, Insurance, and Risk Management), Emerald Publishing Limited, Leeds, pp. 245-282. https://doi.org/10.1108/978-1-80382-027-920231013