Insights into Toronto's Foodservice Market using Data Science Tools

Abstract
This paper delivers valuable decision driven insights into Toronto’s foodservice
industry by employing modern-day data science tools. K means, an unsupervised
clustering algorithm is applied to segregate the city’s restaurant market into clusters
based on the types of restaurants established in the city.
Relationship between
foodservice market of a neighbourhood and its location relative to the city centre along
with relationships within various types of restaurants are analysed using inferential
statistics.
Keywords— Data science, k-means clustering, Pearson correlation, linear regres-
sion, p-value, statistical significance, web scraping, API, market insights

Website