Authors : Dr. G. Amudha; Balaji S; Gowtham H; Sudharshan Kumar M

Volume/Issue : Volume 8 - 2023, Issue 12 - December

Google Scholar : http://tinyurl.com/ynafpk4c

Scribd : http://tinyurl.com/msd7exnc

DOI : https://doi.org/10.5281/zenodo.10389827

Abstract : Traditional taxi systems in urban areas often face inefficiencies caused by uncoordinated actions as customer demand fluctuates. To forecast the upcoming number of taxis, we consider the taxis and uber demand in every region as a time-series data and simplify this prediction problem to a time series prediction. The varying temporal regularity of time series is addressed here. Furthermore, this lack of coordination leads to decreased passenger satisfaction due to long waiting times. The uber and taxi demand is predicted to avoid these inefficiencies. The Data is collected by using networked sensors and info like passenger count, demand rates in locations upon a date is stored as critical data in this system. This data presents opportunities to develop an intelligent transportation system that can efficiently control and coordinate taxis on a large scale. Taxi drivers can navigate to areas with high- demand, while ride-sharing companies like Uber can proactively reallocate the available resources to meet the rising demand