Title: Categorisation of mergers and acquisitions in Japan using corporate databases: a fundamental research for recommendation
Authors: Bohua Shao; Kimitaka Asatani; Ichiro Sakata
Addresses: Department of Construction Management and Real Estate, School of Economics and Management, Tongji University, Tongji Building A, Siping Road 1500, Shanghai 200092, China ' Department of Technology Management for Innovation, Graduate School of Engineering, The University of Tokyo, 7-3-1 Hongo, Bunkyo-ku, Tokyo 113-8656, Japan ' Department of Technology Management for Innovation, Graduate School of Engineering, The University of Tokyo, 7-3-1 Hongo, Bunkyo-ku, Tokyo 113-8656, Japan
Abstract: Mergers and acquisitions (M&A) are recognised as an important strategy for corporate growth. In practice, M&A business requires significant time and energy investment and often fails. Hence, scientific M&A recommendation research is needed under such conditions. This study focuses on M&A categorisation, which is fundamental for M&A recommendation. In this study, we used M&A data, financial data, and corporate data for M&A analysis. We found that the comparison of some financial indicators between the pairs of companies is informative for their relationships. We designed 14 features and used K-means clustering to categorise M&A cases. The 14 features are the features of acquirers, target features, and their relationship features. The M&A cases are categorised into clusters of distinctive characteristics such as additional consideration, high leverage, abundant experience, and more. Finally, we anticipated the M&A motivations of each cluster from these characteristics as well.
Keywords: artificial intelligence; AI; clustering; mergers and acquisitions; M&A; prediction; recommendation; Japan.
International Journal of Technology Management, 2023 Vol.93 No.3/4, pp.316 - 344
Accepted: 12 Jul 2022
Published online: 05 Oct 2023 *