<p>The p-Δ effect is a second-order non-linear effect that is observed in the structural analysis of tall and slender buildings of height equal to or more than 75&#xa0;m. It is related to the additional moments generated due to the combination of lateral displacements and axial loads in a structure. This effect comes into action when the structure reaches a greater height. This research is a unique approach to predict the p-Δ effect using random forest (RF), extreme gradient boosting (XGBoost), artificial neural networks (ANN) and supervised machine learning (SVM). This effect is considered critical in tall structures because lateral displacements amplify internal moments. The approaches that are generally adopted involve computational methods that are iterative in nature, which may not be feasible for all practical scenarios because of higher consumption of time. The model is trained using simulated data that was established using extended three-dimensional analysis of building systems (ETABS) software. The research aims to provide a faster and more reliable alternative method to traditional p-Δ analysis methods. In the study, it is found that XGBoost is a better machine learning algorithm alternative to predict such structural parameters over RF, ANN and SVM. With a higher R² score it proves its efficiency as well as with lower statistical error indicator values the accuracy of the model becomes evident in comparison to RF, ANN and SVM. All the results favour XGBoost as an effective and efficient machine learning algorithm.</p>