Abstract
The paper analyses and explores the possibility of determining the usage of statistical models to aid decision-making during bank mergers, especially in forced mergers. Using models such as Data Envelopment Analysis (DEA) could benefit and enhance informed decisions on bank mergers. We demonstrate the DEA model's efficacy for selecting partners in mergers and acquisitions using the context of bank mega-mergers in India in 2019. Using the semi-parametric Malmquist productivity index, we find that efficiency measured as a change in the total factor productivity (TFP) could not explain the selection of the target and acquirer. Further, the study observes that other considerations such as capital, non-performing assets ratio, geographical dominance, IT platform, and bank size could not reasonably explain most merger combinations. This study shows that using statistical models in policy decision-making may enhance the quality of decisions.