ORDER ARTICLE PERMISSIONS/REPRINTS/OFFPRINTS/TEACHING NOTE
To order permissions to include this article in textbooks, edited volumes, course booklets, online/digital course packs, etc., and/or to order multiple individual hard copies for classroom use, please contact the copyright owners, NeilsonJournals' Publishing Editor, Peter Neilson at pneilson@neilsonjournals.com
How to Make Indians Happy? Using Explainable AI to Identify Happiness Indicators
Manohar Kapse and MA Sanjeev
Jaipuria Institute of Management - Indore Campus, Indore, India
Vinod Sharma and Yogesh Mahajan
Symbiosis Centre for Management and Human Resource Development (SCMHRD), Symbiosis
International (Deemed University), Pune, India
Volume 17: 2024, pp. 55-62; ABSTRACT
India, the world's fastest-growing major economy, remains a bright spot amid global
recession concerns. However, despite its economic success, the country faces challenges in
enhancing the happiness of its over 1.4 billion citizens, ranking a low 126th out of 146 nations in
the recent World Happiness Report (WHR). Although the central and state governments have
introduced various happiness measurement and promotion schemes, achieving significant
improvement in WHR rankings remains elusive. The WHR data offers valuable insights for
policymakers to understand the factors affecting happiness, its cross-cultural differences, and
impact on productivity. Governments and organizations can use such insights to develop both global
and localized strategies to improve citizen well-being and improve productivity. This case examines
how explainable AI (XAI) and machine learning (ML) can be leveraged to identify key happiness
indicators and integrate it with organizational behaviour principles to leverage employee
performance. Students are tasked with analysing global and local drivers of happiness and
developing predictive models using AI and ML tools.
Keywords: subjective well-being, organization behaviour, machine learning, explainable AI (XAI),
support vector machine, random forest, gradient boosting regressor, decision tree, multiple
perceptron neural network.
