Analyzing the Impact of Machine Learning on Improving Corporate Cash Flow Forecasting: A Mixed Qualitative-Quantitative Approach

Abstract

Accurate cash flow forecasting is one of the most critical challenges in financial management, as improvements in this area can lead to reduced financial risks and enhanced decision-making efficiency. In recent years, machine learning algorithms have emerged as effective tools for modeling and forecasting cash flows. This study employs a mixed-method approach. In the qualitative phase, semi-structured interviews with 25 financial managers of Tehran Stock Exchange-listed companies were conducted to identify key challenges and benefits of using machine learning in this domain. In the quantitative phase, financial data from 50 publicly traded firms from 2015 to 2024 were analyzed using linear regression, artificial neural networks, and boosting models such as XGBoost. The results indicate that machine learning algorithms outperform traditional models in cash flow forecasting accuracy. However, challenges such as algorithmic complexity, the need for large datasets, and issues related to model transparency hinder widespread adoption. This study provides recommendations for facilitating the implementation of machine learning in cash flow forecasting, offering valuable insights for financial managers and investors.