For predicting the cab rental fare (CRF), a historical dataset plays a crucial role in applying a suitable machine learning algorithm, where Machine learning (ML) is a part of Artificial intelligence (AI), which makes predictions using past information and applies a suitable algorithm to find patterns in data. In the proposed work, the researchers have used random forest, decision tree, and gradient boosting algorithms to predict the fare amount. It is required to determine the best algorithm that can be applied to test data for that purpose; error metrics are also used in the proposed work. Root mean square error (RMSE) and R2 metrics are used to determine the best model among all the models that can be applied to the training dataset. Researchers have analyzed fare amount using various independent variables such as passenger count, distance, pickup hour, and pickup year. The objective of the proposed work is to create a predictive model that can effectively calculate CRF using different input variables. The outcome from the proposed research can be useful for cab rental companies to predict the CRF and to optimize their pricing strategies accordingly.