Ứng dụng phương pháp học máy nghiên cứu ảnh hưởng của các quyết định tài chính đến giá trị doanh nghiệp

Abstract

This study utilizes machine learning models and traditional statistical methods to analyze the impact of financial decisions on the value of listed firms in Vietnam. The data used in the article was collected from 646 listed firms on the HOSE and HNX exchanges from 2012 to 2022. The study experimented with the dataset using machine learning models: Linear Regression (LR), LASSO, Generalized Additive Model (GAM), Random Forests (RF), Gradient Boosting Regression Trees (GBRT), single-layer and feed-forward neural networks (NN), as well as traditional statistical methods. The results indicate a positive correlation between investment and financing decisions and firm value during the research period. Additionally, the impact of dividend payment decisions on company value is statistically insignificant. Based on these results, the article suggests recommendations to help firms make suitable financial decisions.