Outly

Outly makes recommendations to Capital One customers about stores they would like to try. Since Capital One has data on their customers' financial situation and transaction history, they are in a unique position to make recommendations about future purchases, especially when that data on individuals is combined with the information Capital One has on its merchants, as well as Wolfram Alpha's macro data on the state of the economy. Outly combines all of these datapoints in a machine-learning algorithm to predict the kinds of stores that customers will like, allowing financial institutions like Capital One to help their customers in a new way.

Inspiration

In April 2014, a report released by Ypulse stated that 63 percent would rather buy products from small businesses that offered fewer choices but innovated in its industry, than purchase something from a big brand with options but little innovation. This trend is an enduring and powerful factor in the positioning of companies in their markets, in advertising, and in innovating the next new standard for consumers.

What It Does

Outly is presented in a way that allows you to easily determine the best and worst places to launch a startup. Information about public transportation, local businesses, and crime information are all aggregated on a single map to give you a quick overlay of both historical and real-time information that will allow you to quickly decide where you want to launch a startup.

Challenges We Ran Into

We looked at Yelp data for cafes, restaurants, and other businesses. We used a combination of k-means (unsupervised learning) and SVM (supervised learning) clustering to compute geographic clusters of restaurants, cafes, and businesses, built a regression model using the most significant features in the data to predict success for a new business. Finally, we plotted all real estate listings in the neighbourhood, overlaid with our computed suggestions for good locations to start your new business.

Share this project:
×

Updates