Applications of Machine Learning and Determinants of Dividend Decision : Evidence from Indian Firms

Abstract

Purpose : The theories of dividend decision have disentangled the firms’ critical drivers of the dividend announcement, and their performances are empirically evaluated by employing ordinary least squares (OLS). However, after more than half a century of research, the debate over the determinants of dividend policy in firms is inconclusive. Therefore, the current study attempted to contribute to the literature by exploring new insights into the dividend decisions of Indian firms by employing machine learning. Methodology : This study is based on secondary data, and empirical analysis has used a novel dataset of 919 listed Indian nonfinancial firms from 1999–2019. The study utilized the least absolute shrinkage and selection operator and logistic regression methodologies. Findings : The findings revealed that the idiosyncratic variables are critically significant for dividend announcements by Indian firms. The results demonstrated that large, profitable, liquid, and firms with high market share were more likely to announce dividends in India than small, loss-making, illiquid, and low-market share firms. The direct relationship between Tobin’s Q and the likelihood of paying dividends is a new insight into the dividend decision for Indian firms. Practical Implications : The results will guide the dividend seeker investors to hold the shares of a high market share firm to receive the expected dividend. Originality/Value : This current study extended the literature by studying the dividend decisions of Indian firms by employing the machine learning methodology.