Authors :
O.J. Timilehin; O.A. Balogun; M.A. Dosunmu
Volume/Issue :
Volume 7 - 2022, Issue 1 - January
Google Scholar :
http://bitly.ws/gu88
DOI :
https://doi.org/10.5281/zenodo.5923181
Abstract :
This work looked into the ban of bike hailing
activities which came into effect in the year 2020 by the
Lagos state government. The work looked into the
various angles that may have influenced this decision
and what factors influenced the earning potential of bike
riders. We made use of very limited data due to the
reluctance of bike hailing companies to release more and
initial analysis showed that there were a lot of
discrepancies embedded in it. Using data pre-processing
techniques, we were able to get more insight and carried
out machine leaning classification operations consisting
of Linear Regression, K-Nearest Neighbor, and Support
Vector Classifiers to determine the most influencing
earning factors. Results showed that all three methods
performed averagely and it was recommended that more
accurate and voluminous data will be required to predict
better results.
Keywords :
Transportation, Machine Learning, Information technology, Hailing services, Ban
This work looked into the ban of bike hailing
activities which came into effect in the year 2020 by the
Lagos state government. The work looked into the
various angles that may have influenced this decision
and what factors influenced the earning potential of bike
riders. We made use of very limited data due to the
reluctance of bike hailing companies to release more and
initial analysis showed that there were a lot of
discrepancies embedded in it. Using data pre-processing
techniques, we were able to get more insight and carried
out machine leaning classification operations consisting
of Linear Regression, K-Nearest Neighbor, and Support
Vector Classifiers to determine the most influencing
earning factors. Results showed that all three methods
performed averagely and it was recommended that more
accurate and voluminous data will be required to predict
better results.
Keywords :
Transportation, Machine Learning, Information technology, Hailing services, Ban
