Part of the team of
RYAN BILEK,
Texas A&M University
COLE BOGGUS,
Texas A&M University
ISAAC DECASTRO,
Texas A&M University
JACOB ERICSON,
Texas A&M University
AMIR KARIMLOO,
Texas A&M University
Bike sharing is becoming a common choice among new students on campus who do not want to purchase a bike or live far away from campus. As of 2019, Texas A\&M University has the largest university bike sharing system in the nation. Texas A\&M Transportation Services provide data on bike sharing that is not currently being utilized to improve the efficiency and the effectiveness of the bike sharing system. One of the key factors for increasing the efficiency and the effectiveness of the bike sharing system is placing bike stations at locations with high trip demand. As the locations of bike rentals and returns at different stations are at times not distributed optimally, the bikes in a system need to be re-balanced frequently. Bike sharing companies often have to locate and physically transfer the bikes into transport vehicles, then relocate them into high traffic areas where they are picked up most often. Knowing where high traffic is expected could increase the efficiency and the effectiveness of the bike sharing system. Applying predictive models and machine learning algorithms can be used to accurately forecast high traffic areas during specific times of the day where Texas A\&M Transportation could reallocate the bikes. Furthermore, a heat map and other data visualization tools could be used to display the high traffic areas to users.
https://gisday.tamu.edu/sessions/#/details/db28cdf6-7e2e-494d-8439-eafd6533ba99