Abstract: In response to the widespread issue of cost overruns in construction projects and the limitations of traditional cost prediction methods in handling project dynamics, this study develops a machine learning-based dynamic cost prediction model by incorporating key dynamic influencing factors such as material price fluctuations, design change frequency, and labor productivity variations. A systematic comparison was conducted on the predictive performance of four algorithms: multiple linear regression, support vector machines, random forests, and Long Short-Term Memory (LSTM) networks. Empirical analysis based on 50 historical project datasets demonstrates that machine learning models significantly outperform traditional methods in prediction accuracy, with random forests and LSTM networks showing the best performance. The LSTM model, in particular, exhibits distinctive advantages in capturing temporal cost characteristics. This research provides a practical decision-support tool for cost control throughout the project life cycle.