The optim*um service
- Categorizing preferences of customers or users, as customers forge relationships to the products (content-based recommendations)
- Forging relationships between users in order to fill the lack of knowledge about the preferences of User A with the knowledge about User B (collaborative filtering)
- Negotiating the “cold start problem” by combining content recommenders and collaborative filtering. We also utilize bandit algorithms.
- Use cases of recommendation systems, e.g.:
- product recommendations in online shops
- Support in forming a range of products or services
- Filtering and assorting of search results
- Partially automated customer support
What makes *um better?
In developing customized recommender solutions for our clients based on state-of-the-art machine learning processes, we enable them to gain a competitive advantage. We believe there is no such thing as a ready-made solution. We work together with our clients to find the right solution for them, whether that is B2C or B2B. We do not limit ourselves to only the traditional website use cases; we also develop recommenders for internal processes, expert support or process optimization.
Our Big Data Team possesses extensive sector-spanning experience in the field of data science and machine learning. With a mix of mathematicians, psychologists, physicists and computer scientists, the team is able to examine the various facets of a data problem from a wide range of angles. We stay on the cutting edge of research and do not shy away from technical innovations.