Machine learning software solutions for real estate companies
Elegant solutions to complex real estate problems
Every real estate development project presents unique complexities. We help our clients adapt to new challenges seamlessly with custom, flexible, modular software and client-friendly maintenance commitments.
Sample Solution: Condo Unit Pricing Software
Client: A leading new condo sales/marketing consulting company
Problem: Only top executives could price units, and it was extremely time-consuming.
Solution: Flexible workflow software to streamline and automate condo unit pricing.
Launching an ML project can be simple and low-risk
Our clients want to grow and problem-solve with ML, but don't necessarily know where to start.
We will present our qualifications, our process, and a variety of past work to give you confidence in our team, and a peek at what's possible.
We will introduce ourselves to your working group, share relevant sample projects, and guide a brainstorming session around business problems that can be tackled with ML.
We will use our knowledge and experience to distill your ideas into a few low-risk, high-reward ML product proposals. We'll present a vision for each for your consideration, and answer all of your questions.
If you choose to advance to the Scoping Phase for a product, we will create a detailed proposal of its features, data requirements, timeline and cost.
Our team won 1st place and $1M in the world's biggest machine learning competition
We were part of the team that won the $1M Zillow Prize for improving a home value prediction challenge.
The algorithm won by a comfortable margin, beating more than 3800 teams from 91 countries.
Prize winner in the Two Sigma Financial Modeling Challenge
We were part of the 2nd place, prize winning team of the Two Sigma Financial Modeling Challenge against 2000 teams. The model searched for signal in financial markets data with limited hardware and computational time accurately predicting financial movements.
Prize winner in the 2018 ACM WSDM recommendation challenge
The algorithm helped Asia's leading music streaming service recommend more relevant music to its listeners.
Prize winner in the Home Depot Search Relevance Competition
A Mindler was part of the 2nd place, prize wining team in the Home Depot Product Search Relevance Kaggle competition against over 2000 data science teams. The algorithm helped them improve their customers' shopping experience by accurately predicting the relevance of search results.
Prize-winner in the Mercari Price Suggestion Challenge
A Mindler was part of the 2nd place, prize winning team of the Mercari Kagglle competition with 2000 competitors. Mercari, Japan's biggest community-powered shopping app, challenged data scientists to build an algorithm that automatically suggests the right product prices to sellers.
Prize Winner in the Rossmann Sales Forecasting Competition
A Mindler ranked 2nd and was a prize winner in the Rossmann Store Sales Kaggle competition against 3,738 data scientists. Rossmann operates over 3,000 drug stores in 7 European countries. Our model most accurately forecasted daily sales using historical sales data, product data, store data, and third party data such as weather and distance to competitors.
Mindle researchers in the news
"Shahbazi has competed in 20 Kaggle events, coming second five times and finishing in the top 15 another five times. He finished in the top five per cent of challengers on contests for everything from a Grupo Bimbo (the Mexican bakery multinational that owns Dempsters, Hostess, Vachon brands in Canada) inventory algorithm, a Home Depot online search relevancy challenge, a drug store sales volume prediction engine, a music recommendation system and even the 2017 Data Bowl that looked at lung-cancer detection".
Toronto man shares $1-million prize for real estate price predictions
"Zillow has slowly improved its Zestimate from a median error rate of 14 per cent when it started in 2006 to 5.7 per cent when the contest began in mid-2017. It's now down to 4.5 per cent nationally (it's higher in some cities and lower in others), and once the winners' tweaks to the algorithm are incorporated, the company expects the error rate to dip to about 4 per cent".
Online real-estate firm Zillow pays three guys, one from Toronto, $1M to improve home-value estimates
"Jordan Meyer of the United States, Chahhou Mohamed of Morocco, and Nima Shahbazi of Canada bested more than 3,800 teams representing 91 countries with an algorithm that beat Zillow's benchmark model (evaluated against real-time home sales between August and October 2018) by approximately 13 percent."
Meet the 'Zillow Prize' winners who get $1M and bragging rights for beating the Zestimate
"It's amazing to know that millions of people will benefit from our ideas," said Shahbazi, who competed as a team with Mohamed against Meyer in the contest's initial qualifier, but who decided to join forces with Meyer for the final round. "We brought every novel idea we could to our code and kept experimenting. For every idea that worked, there were a hundred that didn't work. But we kept going."
Zillow awards $1 million to team that reduced home valuation algorithm error to below 4%
On average, Zillow said, the Zestimate is $10,000 off the actual sale price for a median-priced home of about $223,900, and the information gleaned from the Zillow prize winnings could shave $1,300 off that discrepancy. It also moves the Zestimate's national median error rate below 4%.
Zillow's Zestimate got an upgrade — and this trio got $1 million for the new algorithm
"Drug store giant challenged Kagglers to forecast 6 weeks of daily sales for 1,115 stores located across Germany. The competition attracted 3,738 data scientists, making it our second most popular competition by participants ever. Nima Shahbazi took second place in the competition, using his background in data mining to gain an edge. By fully exploring and understanding the dataset, Nima was able to engineer features that many participants overlooked."
Rossmann Store Sales, Winner's Interview: 2nd place, Nima Shahbazi
"Asked to search for signal in financial markets data with limited hardware and computational time, this competition attracted over 2000 competitors. In this winners' interview, 2nd place winners' Nima and Chahhou describe how paying close attention to unreliable engineered features was important to building a successful model."