Welcome to the Canada Chapters!
There is 1 active chapter in Canada:
Apply here to be a chapter lead for other cities and/or universities in Canada
Edmonton, Canada Chapter
Project Duration: 31st May 2022 – 15th July 2022
4 Weeks of AI experience
Edmonton, Canada Chapter – Predicting Housing Affordability of Canada’s metropolitan region (Beginner friendly)
Chapter Lead – Ankit Gupta
Housing affordability has decreased steadily in Canada’s metropolitan region. An average home buyer has to spend more than 70% of the income on mortgage payments in the Toronto metropolitan city to afford a single-family home. The high price of homes pushes many young buyers out of the housing market. Home affordability is going to worsen over time because of the shortage of houses, preference for single-family homes instead of high-rises, and increasing mortgage rates. There is a need for a study to understand Canada’s future housing affordability and identify which cities will be more prone to the housing crisis.
The project findings will be made public and will be available for the policy-makers to review. The project methodology can be extended to different countries/regions.
The Project Goals
– predicting future housing affordability
– locating cities that are more susceptible to the house price increase.
– developing a heat-zone map to highlight regions with worsening housing affordability.
The Learning Outcomes
- – Learn what Canada’s housing market will look like.
- – Discover features that largely influence housing affordability.
- – Discover open-source data for the challenge and identify if the scope of the project can be extended or modified.
Completed Project(s) of Canada Chapters
AI in Governance – Assess the impact of policies enforced across the world and promote good governance through AI
A lot of countries have implemented a variety of policies to tackle the COVID-19 pandemic and all of them have seen different results to the policies put in place. Depending on location, population, and a variety of different factors different measures have been put in place. Most of the countries implemented lockdowns around the world but some were more successful than others. Vaccine distribution has been done in very different ways.
Our goal would be to analyse all policies, build an NLP-based solution for recommending ideas on how to distribute vaccines and how to better tackle a potential third wave or avoid future pandemics.
The project results will be made open source. The aim is for the model to potentially be used by government agencies to improve governance using AI and reduce any further casualties. The model can be further repurposed to support and build effective policies for any natural calamity in the near future.
The Project Goals
1. Analyze COVID policies around the world
2. Figure out the most important features for policies from each country
3. Perform topic modeling on the policies
4. Build a recommendation system for best policies around the world
5. AI suggests customized policies specific to a region/demographic.
The Learning Outcomes
1. Systematic research on COVID policies around the world.
2. Data collection using web scraping, API calls, flat files
3. Creating a Relational Database on a Cloud platform.
4. Data Analysis on both structured and unstructured data.
5. Feature identification specific to a country.
6. Topic modeling (NLP) on the policies.
7. Build a recommendation system that suggests policies specific to a region/demographic.
Link to the Original Project: Coronavirus: Understanding Policy Effects on Vulnerable Populations
We will be running an AI project soon…. Stay Tuned!
Canada Chapter Leads
Ankit is located in Edmonton, Alberta, and is working as a Senior Business Insights Analyst at TD Bank. He has a master’s and bachelor’s degree in engineering from the University of Alberta, Edmonton, Alberta and the Indian Institute of Technology, India. He has a year of experience in data science where he worked on a variety of machine learning and data analysis projects. He extensively used python, SQL, Pandas, NumPy, PySpark, Plotly, Sci-kit learn, TensorFlow, and Keras in his projects. He believes that ML and AI have brought a unique opportunity to everyone interested in solving legacy problems in a better way. It is a time to leverage the power of data to solve complex problems.