The rapid expansion of ride-sharing services such as Uber has resulted in the generation of extensive trip and fare datasets, creating opportunities to develop accurate fare prediction models. In this study, a Decision Tree Regressor is employed to predict Uber ride fares based on key features including pickup and drop-off locations, trip distance, and passenger count. The simplicity and interpretability of the Decision Tree Regressor make it a suitable model for such regression tasks where transparency is crucial.The model was trained and evaluated on real-world Uber trip data, achieving impressive performance metrics with an R² score of 0.9033, indicating that over 90% of the variance in fare prices can be explained by the input variables. Furthermore, the model attained a Mean Absolute Error (MAE) of 0.8081, a Mean Squared Error (MSE) of 2.3316, and a Root Mean Squared Error (RMSE) of 1.5269, demonstrating its robustness and predictive capability.This research highlights the potential of Decision Tree Regression as an effective and interpretable approach for fare prediction in ride-sharing platforms, providing accurate real-time fare estimates that can improve both customer experience and operational efficiency. The findings suggest that lightweight and explainable models like Decision Tree Regressors can be viable alternatives to more complex machine learning models, especially when computational simplicity and model transparency are prioritized.