Design of an Explanation Interface for Recommender Systems in High Stakes Domains – Bc. Jan Ondruch
Bc. Jan Ondruch
Master's thesis
Design of an Explanation Interface for Recommender Systems in High Stakes Domains
Design of an Explanation Interface for Recommender Systems in High Stakes Domains
Abstract:
Doporučovací systémy jsou vyvíjeny s cílem pomoci uživatelům lépe se rozhodovat při hledání produktů, jako jsou filmy či turistické destinace. Společně s doporučovacím systémem se uživatelské rozhraní zaměřené na vysvětlení stává nepostradatelným nástrojem k objasnění toho, proč a jak se určitá položka doporučuje. To platí zejména v doménách s vysokým rizikem, jako jsou finance, zdraví nebo bydlení …moreAbstract:
Recommender systems are developed to help users make better choices while searching for products such as movies or travel destinations. Together with a recommender system, an explanation interface is becoming an indispensable component to describe why and how a certain item is recommended. This is especially applicable in high stakes domains such as finance, health, or housing, where the importance …more
Language used: English
Date on which the thesis was submitted / produced: 18. 5. 2021
Identifier:
https://is.muni.cz/th/smt4j/
Thesis defence
- Date of defence: 22. 6. 2021
- Supervisor: RNDr. Josef Spurný
- Reader: doc. Mouzhi Ge, Ph.D.
Citation record
ISO 690-compliant citation record:
ONDRUCH, Jan. \textit{Design of an Explanation Interface for Recommender Systems in High Stakes Domains}. Online. Master's thesis. Brno: Masaryk University, Faculty of Informatics. 2021. Available from: https://theses.cz/id/qo0kw4/.
Full text of thesis
Contents of on-line thesis archive
Published in Theses:- světu
Other ways of accessing the text
Institution archiving the thesis and making it accessible: Masarykova univerzita, Fakulta informatikyMasaryk University
Faculty of InformaticsMaster programme / field:
Applied Informatics / Service Science, Management and Engineering
Theses on a related topic
- No theses on a related topic available.