Date of Completion

Spring 5-1-2024

Thesis Advisor(s)

Haim Bar

Honors Major

Statistics

Abstract

In this research endeavor, the capabilities of neural networks are utilized to discern regional patterns within a diverse populace via marathon finishing times. Leveraging two decades of race data from the New York and Boston Marathons, the study aims to develop a predictive model capable of identifying individuals' geographic origins based on their marathon performances. This exploration holds promise in shedding light on the intersection of environmental variables and ultimate race achievements in the realm of marathon running. Preliminary results suggest that finishing times alone introduce an excess of randomness that is difficult for the algorithm to untangle, resulting in subpar prediction accuracies. Without clear explanation, certain regions are much more predictive for each of the two major marathons studied. Suggestions for improvement in future works are introducing new, personal data in addition to the finishing time to provide more information to train the models.

Share

COinS