Predicting cash holdings using supervised machine learning algorithms


Creative Commons License

Ozlem S., Tan Ö. F.

FINANCIAL INNOVATION, cilt.8, sa.1, 2022 (SSCI) identifier identifier identifier

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 8 Sayı: 1
  • Basım Tarihi: 2022
  • Doi Numarası: 10.1186/s40854-022-00351-8
  • Dergi Adı: FINANCIAL INNOVATION
  • Derginin Tarandığı İndeksler: Social Sciences Citation Index (SSCI)
  • Anahtar Kelimeler: XGBoost, MLNN, Cash holdings, Turkey, Machine learning, FINANCIAL CRISIS, AGENCY COSTS, FIRMS HOLD, CORPORATE, DETERMINANTS, BEHAVIOR, POLICY, CREDIT, INSIGHTS, PRICES
  • Marmara Üniversitesi Adresli: Evet

Özet

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 R-2 values. Meanwhile, more complex algorithms, such as DT and especially XGBoost, derive higher accuracy with a 0.73 R-2 value. Therefore, using advanced machine learning algorithms, we may predict cash holdings considerably.