Dynamic Pricing using Machine Learning for Emerging Ride-on-demand Service

Muhammad, Abdur Rabb (2024) Dynamic Pricing using Machine Learning for Emerging Ride-on-demand Service. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration Manual) Download (1MB) | Preview

Abstract

The application of machine learning presents considerable opportunities for enhancing dynamic pricing mechanisms in ride-hailing services, particularly in response to swift variations in supply and demand. This study utilised historical data from Uber rides in New York City, following the CRISP-DM framework, to examine essential factors including ride distance, time of day, and number of passengers. Among these variables, ride distance was identified as the paramount factor influencing fare, whereas the number of passengers demonstrated negligible effects. Indeed, Gradient Boosting Regressor outperformed the three models, namely Linear Regression, Random Forest, and Multi-Layer Perceptron, with a mean absolute error of 0.2550 and an R² of 0.8036, thereby effectively modelling nonlinear relationships relevant for dynamic pricing.

Despite this, the adopted modelling is limited within this inquiry, due to the nonavailability of any real-time data and other outside factors such as traffic and weather. Unfortunately, in this instance, it was necessary to rely on a historical dataset from 2009 to 2015. If these factors were taken into consideration, together with an investigation of hybrid modelling techniques, this would clearly provide more adaptability and responsiveness. In conclusion, the findings and results clearly show how machine learning can produce dynamic pricing methods that balance profitability with customer satisfaction in the ride-on-demand marketplaces.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Hamill, David UNSPECIFIED
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Ciara O'Brien
Date Deposited:	01 Sep 2025 13:32
Last Modified:	01 Sep 2025 13:32
URI:	https://norma.ncirl.ie/id/eprint/8667

Actions (login required)

View Item