Paper Title
Data-Driven Valuation of Construction Companies: Leveraging Machine Learning for Enhanced Accuracy in Mergers and Acquisitions

Abstract
Accurate valuation of construction companies is essential for investment decisions, mergers, and acquisitions. Traditional valuation models, such as the discounted cash flow (DCF) method and comparable company analysis (CCA), rely on financial forecasting and expert judgment, often leading to subjectivity and inconsistencies. This study explores the use of machine learning techniques, particularly Random Forest and Artificial Neural Networks (ANN), to predict company valuations based on key financial indicators. The methodology includes comprehensive data preprocessing, feature engineering, model training, and performance evaluation. Cross-validation was employed to ensure model robustness, and feature importance analysis was conducted to determine the most impactful financial predictors. The results indicate that the Random Forest model achieved an R-squared of 0.935, demonstrating strong predictive capabilities, with total assets and EBITDA emerging as the most influential features. The ANN model also showed promising results, with an R-squared of approximately 0.9 and a low RMSE of 0.39. The study highlights the advantages of machine learning over traditional valuation methods in handling large datasets, identifying complex patterns, and improving accuracy. Future work should focus on integrating macroeconomic indicators and enhancing interpretability for practical deployment in financial decision-making. Keywords - Machine Learning, Valuation, Artificial Neural Networks (ANN)