Application of Extreme Gradient Boosting Based on Grey Relation Analysis for Prediction of Compressive Strength of Concrete

The prediction of concrete strength is an interesting point investigation and could be realized well, especially for the with complex system, development machine learning artificial intelligence. Therefore, excellent algorithm should put emphasis to receiving increased attention from researchers. This study presents a novel predictive system as follows: extreme gradient boosting (XGBoost) based on grey relation analysis (GRA) predicting compressive containing slag metakaolin. One its highlights feature selection methodology, i.e., GRA, which was used determine main input variables. Another highlight that performance compared frequently neural network (ANN) genetic algorithm-artificial (GA-ANN) by using random dataset same testing datasets. For three datasets, average R2 values ANN, GA-ANN, XGBoost are 0.674, 0.829, 0.880, respectively, indicating has highest absolute fraction variance (R2). can provide best result root mean squared error (RMSE) percentage (MAPE). RMSE 15.569 MPa, 10.530 9.532 those MAPE 11.224%, 9.140%, 8.718%, respectively. Thus, definitely performed better than ANN GA-ANN. Finally, type application software developed practical applications. vivid interfaces help users in easy efficient analysis.