Predicting cash holdings using supervised machine learning algorithms

被引：0
作者：
Şirin Özlem
Omer Faruk Tan
机构：
[1] MEF University,Department of Industrial Engineering, Faculty of Engineering
[2] Marmara University,Department of Accounting and Finance, Faculty of Business Administration
来源：
Financial Innovation | / 8卷
关键词：
XGBoost; MLNN; Cash holdings; Turkey; Machine learning; C38; C53; G30;
D O I：
暂无
中图分类号：
学科分类号：
摘要：
This study predicts the cash holdings policy of Turkish firms, given the 20 selected features with machine learning algorithm methods. 211 listed firms in the Borsa Istanbul are analyzed over the period between 2006 and 2019. Multiple linear regression (MLR), k-nearest neighbors (KNN), support vector regression (SVR), decision trees (DT), extreme gradient boosting algorithm (XGBoost) and multi-layer neural networks (MLNN) are used for prediction. Results reveal that MLR, KNN, and SVR provide high root mean square error (RMSE) and low R2 values. Meanwhile, more complex algorithms, such as DT and especially XGBoost, derive higher accuracy with a 0.73 R2 value. Therefore, using advanced machine learning algorithms, we may predict cash holdings considerably.
引用
收藏
相关论文
共 180 条
[31]  
Bigelli M(2008)On the determinants of SME cash holdings: evidence from Spain J Bus Financial Acc 17 133-564
[32]  
Sánchez-Vidal J(2021)Implementing machine learning methods in the prediction of the financial constraints of the companies listed on Tehran's stock exchange Int J Finance Manager Account 29 523-60
[33]  
Boubakri N(2017)The financial determinants of corporate cash holdings in an oil rich country: evidence from Kingdom of Saudi Arabia Borsa Istanbul Rev 17 45-750
[34]  
Ghoul S(2016)Policy uncertainty and corporate investment Rev Financial Stud 42 741-13
[35]  
Saffar W(2007)International evidence on the non-linear impact of leverage on corporate cash hodings: the case of corporate cash holdings J Multinatl Financ Manag 2 1-14
[36]  
Breiman L(2015)Credit scoring using the clustered support vector machine Expert Syst Appl 83 1-329
[37]  
Cai W(2018)Digitalisation and big data mining in banking Big Data Cogn Comput 76 323-360
[38]  
Zeng C(2019)A new perspective of performance comparison among machine learning algorithms for financial distress prediction Appl Soft Comput J 3 305-359
[39]  
Lee E(1986)Agency cost of free cash flow, corporate finance, and takeovers Am Econ Rev 33 335-574
[40]  
Ozkan N(1976)Theory of the firm: Managerial behavior, agency costs and ownership structure J Financial Econ 30 568-12
12345678910