yasminemmahmoud / ibm-data-science-capstone

IBM Data Science Capstone Project- Opening a Bakery in Toronto,CA

IBM Data Science Capstone Project - Yasmine Mahmoud

The Best Neighborhood in Toronto to open a Gluten Free Restaurant and Bakery

1. Introduction

For the last few months, I have been working on earning the IBM Data Science professional certificate. IBM Data Science professional certificate is a set of specialized courses with hands on Labs designed to train you to work as a Data Scientist.

The courses are very engaging with real datasets and real world problems to work on.

The Specialization consists of 9 courses: Data science Methodology, Tools for Data Science, Python for Data science and AI, Databases and SQL with Python, Data analysis with Python, Data visualization with Python, Machine Learning with Python and lastly, the Capstone project where you define a problem, describe and collect data from online resources to create a solution for an exciting problem.

In this blog, I explain my process for determining the perfect spot to open a Gluten Free restaurant in Toronto, Canada. Along the way, I will explain all the processing steps starting with problem formulation, data preparation, methodology, the data analysis and visualization and lastly, the machine learning algorithm to predict the perfect spot for the restaurant.

2. Business Problem

We're more than a decade into the Gluten Free market growth. Thanks to increased awareness of Celiac Disease and gluten sensitivity -- and improving rates of diagnosis, there is a variety of Gluten Free products in almost every grocery store.

While demand for gluten free meals in restaurants eventually gives those affected with Cliac disease and health conscious individuals more choice, the situation does come with pitfalls. The most important one, is the need to ensure that any restaurant with a gluten free menu knows not just what ingredients are used in their recipes...but how to safely prepare the meal without putting you at risk from gluten cross contamination.

The next important pitfall, is that It's not unusual to go into a restaurant that advertises gluten-free food and be told you can have dry meat, a baked potato or french fries (only they're from a shared fryer when you ask), and the vegetable of the day, plain. If there is a gluten-free dessert, it's typically a brownie. So, you basically feel like a second-class citizen in most restaurants.

3. Target Audience

Since people around the world are becoming more and more conscious of what they put into their bodies and how that impacts their health, opening a Gluten Free Restaurant and Bakery in Toronto will attract a large audience, not only those affected with Cliac disease.

This project demostrates to investors that opening a Gluten Free Bakery is a lucrative business idea.

4. The Data

The following Datasets contain various unique information about Toronto and its neighborhoods to discover the best spot to open a Gluten free Bakery:

4.1 Foursquare Location Data: to get the location and venue information (https://developer.foursquare.com/docs)

4.2 Neighborhood Profiles Data: To get detailed information about each neighborhood in Toronto. (https://open.toronto.ca/dataset/neighbourhood-profiles/)

4.3 Neighbourhoods Dataset: To get information about Toronto neighborhoods such as location, and the name of all the neighborhoods present in Toronto. (https://open.toronto.ca/dataset/neighbourhoods/)

5. Methodology

After cleaning and exploring the data, we will apply the K-means machine learning algorithm to create clusters of Toronto neughborhoods and choose the best spot(s) to open a bakery.