Recommendation Recovery with Adaptive Filter for Recommender Systems

BLANCO SÁNCHEZ, José Miguel, Mouzhi GE a Tomáš PITNER. Recommendation Recovery with Adaptive Filter for Recommender Systems. Online. In Proceedings of the 17th International Conference on Web Information Systems and Technologies - WEBIST. Setúbal, Portugal: SciTePress/INSTICC, 2021, s. 283-290. ISBN 978-989-758-536-4. Dostupné z: https://dx.doi.org/10.5220/0010653600003058.

Základní údaje

Originální název

Recommendation Recovery with Adaptive Filter for Recommender Systems

Autoři

BLANCO SÁNCHEZ, José Miguel (724 Španělsko, garant, domácí), Mouzhi GE (156 Čína) a Tomáš PITNER (203 Česká republika, domácí)

Vydání

Setúbal, Portugal, Proceedings of the 17th International Conference on Web Information Systems and Technologies - WEBIST, od s. 283-290, 8 s. 2021

Nakladatel

SciTePress/INSTICC

---

Další údaje

Jazyk

angličtina

Typ výsledku

Stať ve sborníku

Obor

10201 Computer sciences, information science, bioinformatics

Utajení

není předmětem státního či obchodního tajemství

Forma vydání

elektronická verze "online"

Kód RIV

RIV/00216224:14330/21:00122770

Organizační jednotka

Fakulta informatiky

ISBN

978-989-758-536-4

ISSN

DOI

http://dx.doi.org/10.5220/0010653600003058

UT WoS

000795868100028

Klíčová slova anglicky

Recommender Systems; Recommendation Recovery; Adaptive Filter; User-oriented Recommendation

Štítky

firank_B

---

Anotace

V originále

Most recommender systems are focused on suggesting the optimal recommendations rather than finding a way to recover from a failed recommendation. Thus, when a failed recommendation appears several times, users may abandon to use a recommender system by considering that the system does not take her preference into account. One of the reasons is that when a user does not like a recommendation, this preference cannot be instantly captured by the recommender learning model, since the learning model cannot be constantly updated. Although this can be to some extent alleviated by critique-based algorithms, fine tuning the preference is not capable of fully expelling not-preferred items. This paper is therefore to propose a recommender recovery solution with an adaptive filter to deal with the failed recommendations while keeping the user engagement and, in turn, allow the recommender system to become a long-term application. It can also avoid the cost of constantly updating the recommender learning model.