• 

  Mock-up from Proof of Concept iOS app

The Story

Re-using is a hassle. It’s tough to know what can and cannot be re-used; it takes time researching; you have to find a suitable place to drop off your old things; and it ends up costing you time and money.

That’s where Divertsy SmartReuse comes in. We offer a free, mobile app that enables consumers to take a picture of their trash which then uses Artificial Intelligence to identify the item and recommend the best options for re-use.

We collect, analyse and sell this consumer data to businesses so that they have a better understanding of consumer behaviors after the point of sale as well as insight into why their products are being binned. We enable businesses to close their loop on their product cycle by connecting them with consumers at the end-of-lie as well as providing an opportunity to promote new products at the exact time consumers need it.

Our application uses state of the art machine-learning leveraging iOS, and integrates seamlessly with a number of current applications such as DonateNYC and eBay. It also allows local communities to post what kind of donations they would appreciate, such as tables and chairs for schools, or clothing for the homeless.

The Technology

In the short hackathon time, we were able to get a proof of concept iOS app running to use an open source machine learning model and test identifying items using an iPhone 6 and recent iPad. We also identified the API services and the waste stream categories that we would need in order to return look up results to the end users.

Having previously developed a waste stream tracking application, we know that having an API based application will allow us to quickly iterate on the development process and separate the front end development from back-end services.

Built With

• api
• machine-learning
• swift