One of Lassonde’s own has won $1 Million dollars as part of the biggest computer science competition in the history of technology, offered by Zillow, a leading real estate and rental marketplace dedicated to empowering consumers with data, inspiration and knowledge.
Dr. Nima Shahbazi entered the Zillow Competition two years ago, balancing the challenge and his PhD studies at the Lassonde School of Engineering, under the supervision of Dr. Jarek Gryz and Aijun An, Professors from the Department of Electrical Engineering & Computer Science.
Shahbazi worked across continents and multiple time zones with a team of two others – one from Morocco and another from the United States, to beat the Zestimate Algorithm. The team's winning solution beat the Zillow Benchmark Model by over 13 percent. They also held a comfortable lead against the second and third place teams.
We spoke with Shahbazi about his experience, how he managed to win the competition and what he plans to do with his winnings.
Q: How did you get involved with the Zillow Competition?
NS: I was always curious about what factors drive housing prices since my wife is an architect and the Toronto real estate market is so competitive. I also thought the size of the prize would attract a lot of other data scientists to the competition and I love a hard challenge!
Q: Did this competition have anything to do with your PhD studies, or was it purely for fun?
NS: Technically speaking my Ph.D. was more about data and pattern mining, this competition was mostly about deep learning and machine learning.
Even more than the prize money, I’m super motivated to compare my capabilities to other data scientists and see my hard work and creativity pay off in the rankings. I guess I’m a bit competitive…
The competition was hosted on Kaggle, Google’s platform for machine learning and data mining problems where they work with top tier conferences like NIPS, ICDM, WSDM, and big companies like Microsoft, Google and Amazon.
Kaggle competitions are a great opportunity for AI scientists to expand their knowledge and challenge problem solving skills on real problems with real data.
Q: How does the work you put into this competition relate back to your research areas of focus?
NS: In my research and in these competitions, I needed to learn the foundations of Machine Learning and data mining as well as math and statistics. There is just so much to learn! Every time I learned something new in math and statistics, it helped me with the competitions and vice-versa.
Q: Explain the process by which you and your team were able to improve the accuracy of the Zestimate?
NS: With so many top teams from around the world, this competition really required novel ideas and problem solving. Our team focused on minimizing the correlation between our insights and then getting the best blend. We each worked on a different model and feature set and communicated actively on Slack to share our insights.
Q: Was it difficult to balance both completing your PhD and working on this Zillow competition?
NS: Well, I worked 7 days a week and passionate about solving problems. I had enough time to work on both parts since I had very limited vacations for the past 4 years! But it was worth it.
Q: Was it difficult working with a team that lived in different countries + time zones? How were you able to make that work?
NS: It was quite challenging, but we actively shared ideas on Slack and codes on Github. Jordan and I were in the same time zone but our Moroccan friend, Chahhou, was six hours ahead of us. Our poor computers were running 24/7 and when a good result came out, we updated our shared roadmap and kept going.
Q: Any big plans for the prize money?
NS: It’s surreal! I don’t have a specific plan, but I will invest some in my startup Mindle.ai and I will buy gifts for my wife, my Mom and Dad and my two sisters. We could all use a trip somewhere hot!
Join us in congratulating Nima!