Machine Learning in a real-life app

With this talk we want to inspire other developers to use machine learning in their apps.

In the past months we had to build an image recognition feature in the iOS and Android app of a large retailer. The image recognition model has to match the product from a photo with the correct product in the product range of the retailer, which contains about 20,000 products. To achieve this we have built a custom machine learning model.

There are a lot of tutorials and a lot of documents of how to implement machine learning models in an app, so this won’t be a step by step tutorial. It’s a talk about the real world challenges. From the first proof of concept to the production version was a bumpy road for us app developers. Working with machine learning models requires a different way of thinking.

If you’re aware of the challenges and know how to implement machine learning, it opens up wonderful opportunities.