Proceedings of the 1st International Conference on Sustainable Management and Innovation, ICoSMI 2020, 14-16 September 2020, Bogor, West Java, Indonesia

Research Article

Bankruptcy Prediction Model using Logit Regression in the Automotive Sector

Download926 downloads
  • @INPROCEEDINGS{10.4108/eai.14-9-2020.2304465,
        author={Nonthawat  Sricharoenchit and Surang  Hensawang},
        title={Bankruptcy Prediction Model using Logit Regression in the Automotive Sector },
        proceedings={Proceedings of the 1st International Conference on Sustainable Management and Innovation, ICoSMI 2020, 14-16 September 2020, Bogor, West Java, Indonesia},
        publisher={EAI},
        proceedings_a={ICOSMI},
        year={2021},
        month={5},
        keywords={bankruptcy prediction logit regression financial ratios corporate governance automotive industry},
        doi={10.4108/eai.14-9-2020.2304465}
    }
    
  • Nonthawat Sricharoenchit
    Surang Hensawang
    Year: 2021
    Bankruptcy Prediction Model using Logit Regression in the Automotive Sector
    ICOSMI
    EAI
    DOI: 10.4108/eai.14-9-2020.2304465
Nonthawat Sricharoenchit1,*, Surang Hensawang1
  • 1: Kasetsart University
*Contact email: bsnonthawat@hotmail.com

Abstract

This research aims to develop the bankruptcy prediction model tool for financial risk management in the automotive industry in Thailand. The study will research the relationship between the company’s status and independent variables that include financial ratios and corporate governance. These factors will be used to find the model that can separate the automotive companies into two groups that are bankruptcy Company and non-bankruptcy Company with a high accuracy rate. The data used in this study are divided into two sample groups, including 56 companies with bankruptcy situations and 101 companies without bankruptcy situations. The data was based on the financial statement in the DBD Data Warehouse, and the status of a company contained in the website using current financial statements and using three-period historical data to define the prediction model. The result shows that the model achieved an overall accuracy rate of 75.40 percent for predicting the company’s status in the automotive industry by using seven independent variables. These are the percentage of Thai shareholders, the share of major shareholders, the number of shareholders, the number of directors, current ratios, operation expense to total revenue ratios, and debt to asset ratios. Therefore, this model can accurately predict the bankruptcy of the company in the Thailand automotive industry.