Forecasting Urban Mobility: A Supervised Machine Learning Approach to Taxi Demand Prediction

Sayantan Chakraborty, Raunak Banerjee, Satadip Banerjee

Abstract: Cities experiencing rapid urban growth increasingly depend on accurate taxi demand forecasts for effective transportation management. This report presents a supervised machine learning approach that leverages historical trip and spatio-temporal data, alongside real-time contextual inputs, to predict taxi demand. (Chen, 2016) The system incorporates data cleaning, feature selection, normalization, and linear regression modeling to enhance prediction accuracy. Experimental results show that the proposed method outperforms traditional forecasting models, delivering more reliable demand predictions under various conditions. These findings support the value of machine learning in optimizing urban mobility and resource allocation. (Vapnik, 1995).

Keywords: Machine Learning, Supervised Learning, Taxi Demand Prediction, Urban Mobility, Data-driven Forecasting