This project is a comprehensive analysis of online taxi pricing, focusing on identifying factors that influence fare rates, customer behavior in response to price changes, and optimal pricing strategies. Utilizing a dataset with attributes such as ride requests, pricing, distances, and durations, we applied Python and libraries like NumPy, SciPy, Scikit-learn, and Pandas for data manipulation, statistical analysis, and predictive modeling.
- To analyze peak and off-peak hours' impact on taxi pricing.
- To investigate the effect of distance and expected duration on fares.
- To understand passenger and driver behavior concerning pricing strategies.
- To develop a predictive model for dynamic pricing.
- Data Processing & Exploration: Leveraging Python for advanced data cleaning, exploration, and visualization.
- Predictive Modeling: Employing machine learning techniques to forecast pricing and demand.
- Behavioral Insights: Analyzing cancellations and preferences related to price adjustments.
- Python
- Pandas for data manipulation
- NumPy and SciPy for numerical and scientific computing
- Scikit-learn for machine learning
- Matplotlib and Seaborn for data visualization
This project was a collaborative effort, providing insights into improving online taxi services' efficiency and profitability through data-driven decision-making.