NORMA eResearch @NCI Library

Taxi Trip Time and Trajectory Prediction Using Machine Learning

Rajani, Janvi Rajesh (2022) Taxi Trip Time and Trajectory Prediction Using Machine Learning. Masters thesis, Dublin, National College of Ireland.

[thumbnail of Master of Science]
PDF (Master of Science)
Download (2MB) | Preview
[thumbnail of Configuration manual]
PDF (Configuration manual)
Download (1MB) | Preview


Predicting route time is critical for both commercial traffic and trip planning. When making judgments, riders will benefit from accurate journey time estimations. As a result, traffic conditions will be improved. Machine learning methods are used to estimate cab travel time and trajectory in this research. Baseline Model, Decision Tree Regression, Lasso Regression, Random Forest Regression, XGBoost Regression, and KNN Regression are used to forecast cab travel time. Multiple Linear Regression and Gradient Boosting Regression are used to forecast cab journey trajectory. The cab ID, timestamp, call type, GPS co-ordinates, and Day type are in the dataset is used for this research. Following that, the performance metrices are used to analyze and compare the outputs of these algorithms. The model with the highest accuracy and lowest error is chosen. Following the evaluation of the models, it was discovered that Lasso regression having MAE=1.01 beats other models in predicting taxi trip prediction, while Gradient Boosting regression having MAE=0.008 outperforms Multiple Linear Regression. The models are also compared to state-of-the-art approaches.

Item Type: Thesis (Masters)
Uncontrolled Keywords: taxi time prediction; trajectory prediction; regression; Machine Learning; Lasso Regression; Gradient Boosting Regression
Subjects: Q Science > QA Mathematics > Electronic computers. Computer science
T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science
T Technology > TE Highway engineering. Roads and pavements
T Technology > TL Motor vehicles. Aeronautics. Astronautics
Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions: School of Computing > Master of Science in Data Analytics
Depositing User: Tamara Malone
Date Deposited: 01 Mar 2023 12:18
Last Modified: 01 Mar 2023 17:30

Actions (login required)

View Item View Item