Skills used: Python, Pandas, SKlearn, Matplotlib
Project Objective: This project aims to predict the trip duration of rental bikes in the Seoul Bike sharing system using data mining techniques and weather data. Accurately predicting trip duration is crucial for the development of Intelligent Transport Systems (ITS) and traveler information systems. To achieve this, the project will utilize the data from the Seoul Bike sharing system, which provides a wealth of information about bike rentals and usage patterns, as well as weather data, which is an important factor affecting trip duration.
The project will use various data mining techniques, such as regression analysis and machine learning algorithms, to analyze the data and develop predictive models. These models will take into account factors such as the time of day, day of the week, weather conditions, and other variables that may affect trip duration.
The expected outcome of this project is a model that can accurately predict trip duration in the Seoul Bike sharing system. This model will be useful for both transportation planners and individual travelers, as it can provide valuable information about travel times and help optimize travel plans. Additionally, the project can be extended to other bike-sharing systems in other cities, making it a valuable tool for the development of ITS and traveler information systems worldwide.
Quantifiable result: Successfully able to predict the Bike rental demand resulting in 94% accuracy.
- Used Random Forest Regressor to predict the number of bikes rented in the city of Seoul
- The data had quite a few categorical variables which were encoded for use in the model
- Encoded categorical variables to numeric using Sklearn due to the presence of many string columns
- Cross Validation for validating the training data and model fit.