High-rise buildings, which have become significant parts of the urban habitat, are particularly notorious for delayed completion times. Though there exist a plethora of studies on construction delays, the problem is insufficient research on prescriptive methods to mitigate delays. This study sought to employ Machine Learning (ML) techniques to learn from historical data on high-rise construction to forecast potential delay times. An input data containing 9 features and 12 cases were used. Initially, five feature sets were built based on the recursive feature elimination process. Further to that was the classification process that employs the following ML techniques: Multi-Linear Regression Analysis (MLRA), k-Nearest Neighbors (KNN), Artificial Neural Networks (ANN), and Support Vector Machines (SVM) to determine delay times. The predictive performance of these techniques was measured by co-efficient (R2) and Root Mean Squared Errors (RMSE). The best three models were SVM with 2 independent variables (R2 0.56, RMSE 1.6), ANN with 2 independent variables (R2 0.49, RMSE 1.83), and KNN with all independent variables (R2 0.46, RMSE 1.71). To improve the predictive performance of developed models, three best performing models were combined using fixed and trained rules. Results showed an improvement for a fixed rule based on minimum values with (R2 0.59, RMSE 1.65). The study has significant implications to avoid delays in high-rise projects to avoid delays, which first employs ML in for the first time.