LEVERAGING MACHINE LEARNING ALGORITHMS TO GAIN INSIGHTS INTO THE MINDSETS OF IT PROFESSIONALS IN MUMBAI

Abstract

Objective of the study: The objective of this study is to employ HR analytics, utilizing machine learning algorithms and descriptive statistical methods on unstructured datasets, to gain insights into the perceptions of employees regarding the organization. The focus is on understanding employee satisfaction levels and discerning factors that influence their mindset, ultimately aiding HR departments and decision-makers in optimizing Return on Investment (ROI) from human capital.

Methodology: In this study, the author utilizes R programming software to comprehensively comprehend and forecast the determinants of job satisfaction. Employing advanced machine learning techniques, specifically text analytics and sentiment analysis, the research aims to predict patterns and discern sentiments and opinions concerning the organization.

Research design and approach: The author distributed open-ended questionnaires to mid-level employees within the IT sector, collecting and analysing a total of 250 responses for this study. The data exclusively pertains to Mumbai, with study limitations acknowledged regarding sample size and employee category. The author sourced data from both multinational IT corporations and national-level companies, recognizing that the study's outcomes may exhibit variations based on diverse sectors and employee hierarchies.

Findings and recommendations: The study reveals that IT employees experience notable work pressure, with challenges related to their ideas being acknowledged by superiors. However, the younger generation expresses contentment with the provided facilities and the overall work environment. Subsequently, the collected data will undergo training and testing processes. Through this, a model will be developed, allowing for the evaluation of methods to predict the probability of an employee either staying or leaving the company.

Keywords: HR analytics, Employee job satisfaction, text analytics, R programming, Sentiment analysis