AI-based product placements to increase revenue
The problem
The project
In the wake of the Covid crisis in 2020, eyewear retailer KRASS Optik faced the challenge of a significant drop in sales in on-site stores. A significant portion of sales was generated through on-site stores until 2020. At the same time, KRASS Optik operated a website for its customers. Although few items had been sold on this website, it became apparent that customers often came to on-site stores with a precise idea of a desired product, found on the website. It was therefore assumed that the website would be a good source of data with regard to the needs of customers. This hypothesis was to be validated within the framework of an AI project and then translated into a solution that recommends glasses for customers on the basis of data in order to increase the probability of a purchase and thus counteract the drop in sales.
The solution
Our contribution
The joint project scope consisted, among other things, of the development of a Customer Data Platform (CDP) for the integration of online (website) and offline (stores, databases) data sources. In particular, the challenge of merging data based on different identifiers had to be solved. Building on the central data platform with interaction data (e.g. purchases, clicks, reservations, dwell times, etc.), a recommender system was developed based on the collaborative filtering approach. The developed system provides product recommendations for individual customers (including new customers) via different channels (website, databases in on-site stores, newsletter) to address customers in a personalized way.
The underlying database is updated daily so that current data is always available. Based on this database, new model versions and recommendations are provided daily. This, as well as the continuous monitoring of the overall system, is ensured by the implemented MLOps infrastructure.
Our result
View more projects
Contact us
- Critical and holistic evaluation of the approach
- Development of guidance for reliable implementation
- Free of charge and without obligation
Start your AI journey with us now
Subscribe now to the Merantix Momentum Newsletter.
View more projects
Contact us
- Critical and holistic evaluation of the approach
- Development of guidance for reliable implementation
- Free of charge and without obligation