International Journal of Innovative Research in Computer and Communication Engineering
ISSN Approved Journal | Impact factor: 8.771 | ESTD: 2013 | Follows UGC CARE Journal Norms and Guidelines
| Monthly, Peer-Reviewed, Refereed, Scholarly, Multidisciplinary and Open Access Journal | High Impact Factor 8.771 (Calculated by Google Scholar and Semantic Scholar | AI-Powered Research Tool | Indexing in all Major Database & Metadata, Citation Generator | Digital Object Identifier (DOI) |
| TITLE | Predictive Analysis of Uber Fare using Machine Learning |
|---|---|
| ABSTRACT | The rise of ride-sharing platforms such as Uber has transformed modern transportation systems by offering convenience, accessibility, and dynamic pricing models. However, fare estimation remains a challenge for both riders and developers due to fluctuating prices influenced by distance, time, location, and demand. This research presents a machine learning-based predictive model to estimate Uber fares using historical trip data. The dataset is preprocessed, engineered, and analyzed using regression-based algorithms, including Linear Regression, Decision Tree Regressor, Random Forest, and XGBoost. The study compares model performances using evaluation metrics such as Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and R² Score. Experimental results indicate that the Random Forest Regressor achieved the highest accuracy, effectively minimizing prediction errors. This work demonstrates how machine learning can enhance fare transparency and improve pricing predictions in the transportation industry. |
| TITLE | |
| AUTHOR | SANKET BHOSALE, RUTURAJ VIDHATE, SHUBHAM ADHAV AND ABHISHEK DHAMANE |
| VOLUME | 176 |
| DOI | DOI: 10.15680/IJIRCCE.2025.1311033 |
| pdf/33_Predictive Analysis of Uber Fare using Machine Learning.pdf | |
| KEYWORDS |
