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