Predicting Demand for Ridehailing Services: Empowering Local Policy Makers

This repository represents the work completed for a data analytics capstone project that aims to predict the demand for ride-hailing services (i.e., Lyft and Uber) in the City of Toronto using regression, time series, and geospatial analysis techniques.

Table of Contents

The repository is divided into subfolders:

• data_explore - Provides an in-depth exploration of the ridehailing and weather datasets
• analysis_pred - Provides further analysis to support data cleaning, test different time-series modelling methods, and predict ridehailing trip demand
• final_report_code - Identififes the optimal method to predict demand for ride-hailing services

Contact

Matthew Lee [email protected]