ITDS | SPMS

RIDE EXPRESS PREDICTIVE MODELING

Project Description
Supervisor

To have a better experience and utilization of resources as well as improve service delivery, this study focuses on predicting the estimated timeliness for each ride of the express vehicle. The duration of the ride express could affect the level of services offered at any particular station. This study embarks on the use of complex machine learning approaches, capable of predicting the duration of each trip made by a ride express. In their complexity handling in real-life situations, it is important not to ignore existing regression-based approaches; this examination of this proposal commences with this point. We then propose a machine-learning framework that supports historical trip data, cleans and preprocesses it, and employs both Linear Regression and Random Forest Regression models to predict trip durations. Our evaluation metrics, such as Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), and R-squared Score (R²), demonstrate the effectiveness of our models. For Linear Regression, the model achieved the following results: MSE = 256.34, RMSE = 16.01, MAE = 12.53, MAPE = 9.12%, and R² = 0.85. Similarly, for the Random Forest Regression model, the performance was notably better, with MSE = 198.45, RMSE = 14.08, MAE = 10.87, MAPE = 7.56%, and R² = 0.92. These findings indicate that our machine learning algorithms, particularly Random Forest Regression, greatly surpass traditional techniques, producing more precise and dependable forecasts. This advancement leads to better passenger service operations through improved trip prediction methodology.

Machine Learning: Machine Learning (ML) research in Computer Science and Information Technology focuses on the development of algorithms and models that enable computers to learn from data and improve their performance over time without being explicitly programmed. It is a subset of Artificial Intelligence that uses statistical techniques to give machines the ability to learn patterns, make decisions, and predict outcomes based on data. Supervised learning, a key area of ML research, involves training models on labeled data, where the input-output relationships are predefined. This method is widely used for tasks such as classification (e.g., spam detection) and regression (e.g., predicting house prices). Unsupervised learning, on the other hand, involves finding hidden patterns in data without predefined labels, with clustering and association being typical applications in areas such as customer segmentation and anomaly detection. Reinforcement learning is another area of ML that focuses on teaching agents to make decisions by interacting with their environment and receiving feedback in the form of rewards or penalties. It is often applied in robotics, game playing, and autonomous systems, where continuous learning and adaptation are required.