[1N4-GS-13] AI application: Machine learning and application (1)

[1N4-GS-13-05] Performance correlation analysis of business-to-business transactions and its application to corporate growth forecast

〇Takahiro Doi^1,3, Shunsuke Ohkoda¹, Takeru Nitta¹, Yoshimasa Hidaka^1,3, Yasuhiro Yamaguchi^1,3, Masaki Yanaoka², Atsushi Takemasa² (1. JSOL Corporation, 2. TOKYO SHOKO RESEARCH, LTD, 3. RIKEN)

Keywords:interfirm networks, corporate growth forecast, complex networks, machine learning

It is important in practice to predict growing companies from data. The purpose of this study is to investigate the performance correlation between companies and apply it to the corporate growth forecast. We use the transaction data of TOKYO SHOKO RESEARCH, LTD as well as the financial data. We found that there is a positive correlation between sales growth rates between companies. Then we performed machine learning analysis for corporate growth forecast including business partner information of forecasting companies. As a result, we confirmed that the performance of prediction is improved. Finally, we compared the results of two cases with/without the information of the business partner.