Dietmar Jannach
Recommender systems researcher and first author of a 2019 review of what recommendations do for a business, as opposed to how accurate they are in a laboratory.
Who they are
Jannach is listed at the University of Klagenfurt on the 2019 paper, written with Michael Jugovac of TU Dortmund, in ACM Transactions on Management Information Systems. The review gathered published field tests of recommender systems. Where sales were measured directly, recommendations raised them by one to five per cent on average. Larger figures, such as a rise of more than 26 per cent for one category of an online grocery store, describe a slice of a shop rather than the whole of it, and baselines were usually no recommender or a popularity list.
The review also reports a news-site test in which a better recommendation method raised clicks by about 35 per cent, while moving and enlarging the recommendation box raised them by about 100 per cent, and a case in which switching a recommender off at an online bookshop cut revenue by 17 per cent.
Key papers
Jannach, D., & Jugovac, M. (2019). "Measuring the business value of recommender systems." ACM Transactions on Management Information Systems, 10(4), 1-23. doi:10.1145/3370082. Preprint arXiv:1908.08328.
Key ideas
See Recommender Systems.
Sources
- Jannach and Jugovac (2019), full text read (arXiv preprint 1908.08328v3), 12 October 2026.