Explainable Recommender Demo

Most retailers agree that they are competing on a highly dynamic environment, and they acknowledge that the way they are doing business now is not how they are going to win in the future.

A recommendation system can be seen as the evolution of search engines. They help the user navigate among hundreds of options, retrieving the products that better fit their preferences.

Being able to provide explanations to the consumer positions your retail as:
- Trustworthy as you are showing that the algorithms are making the correct decisions for the right reasons.
- Transparent as users understand where the recommendations came from.
- Accountable as you taking responsibility of using AI ethically.

With most retailers, we are able to make the integration in two weeks.

We connect our algorithms with your product feed and generate an API. From your web page, a simple query is sent to the API that returns the list of products with the highest likelihood to be bought, and also, provides an explanation of why the user might like the product.

We rely on the most secure clouds to manage our services, like Microsoft Azure or Google Cloud Platform.

We are very serious about privacy as it is stated in our AI POLICY. We commit to incorporating privacy principles in the development and use of our AI technologies. We give opportunity for notice and consent, encourage architectures with privacy safeguards, and provide appropriate transparency and control over the use of data.

Our technology is designed to ensure maximum scalability. On average, 95% of our requests are served in under 40 milliseconds.

Our explainable recommender is based on a retail knowledge graph. A knowledge graph provides two benefits to a recommender: it allows explainable recommendations and it enriches the machine learning features of the model to make it more accurate.

In RecoMind, we own a retail knowledge graph with millions of relationships.