<p>Basalt fiber reinforced concrete (BFRC) is gaining recognition as a promising building material in the recent times because of its improved durability and mechanical properties over conventional concrete. This study examines the flexural strength of BFRC and analyzes the impact of important factors such as curing conditions, w/c ratio, and fiber volume fraction. Experimental results have shown combining basalt fibers into concrete can significantly increase the flexural strength of concrete, thereby enhancing its load bearing capacity and improves its crack resistance. These results prove that BFRC is a suitable material for structures requiring high tensile and flexural performance. To complement the experimental investigation, several machine learning classifiers such as Gradient Boosting, and eXtreme Gradient Boost, K-Nearest Neighbors, Support Vector Regression, Decision Tree, Random Forest, are used to forecast the flexural strength of BFRC. The XGBoost model demonstrated excellent accuracy, achieving R² value of 0.972 for training data, and 0.936 for testing data respectively. In the error analysis, RMSE value was 0.391 during the training, while it was 0.539 during testing, indicating strong generalization capability. This study indicates that the use of machine learning techniques can serve as reliable predictive tools to improve BFRC performance and promote their use in real-world construction practices.</p>