An Adaptive Filter for Preference Fine-Tuning in Recommender
Systems

D 2023

An Adaptive Filter for Preference Fine-Tuning in Recommender Systems

BLANCO SÁNCHEZ, José Miguel, Mouzhi GE a Tomáš PITNER

Základní údaje

Originální název

An Adaptive Filter for Preference Fine-Tuning in Recommender Systems

Autoři

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

Vydání

CHAM, WEB INFORMATION SYSTEMS AND TECHNOLOGIES, WEBIST 2020, WEBIST 2021, od s. 107-121, 15 s. 2023

Nakladatel

SPRINGER INTERNATIONAL PUBLISHING AG

Další údaje

Jazyk

angličtina

Typ výsledku

Stať ve sborníku

Obor

10201 Computer sciences, information science, bioinformatics

Stát vydavatele

Švýcarsko

Utajení

není předmětem státního či obchodního tajemství

Forma vydání

elektronická verze "online"

Kód RIV

RIV/00216224:14330/23:00133947

Organizační jednotka

Fakulta informatiky

ISBN

978-3-031-24196-3

ISSN

DOI

http://dx.doi.org/10.1007/978-3-031-24197-0_7

UT WoS

000972038800007

Klíčová slova anglicky

Recommender systems; Recommendation recovery; Adaptive filter; User-oriented recommendation

Příznaky

Mezinárodní význam, Recenzováno

Změněno: 8. 4. 2024 12:17, RNDr. Pavel Šmerk, Ph.D.

Anotace

V originále

A recommender system may recommend certain items that the users would not prefer. This can be caused by either the imperfection of the recommender system or the change of user preferences. When those failed recommendations appear often in the system, the users may consider that the recommender system is not able to capture the user preference. This can result in abandoning to further use the recommender system. However, given the possible failed recommendations, most recommender systems will ignore the non-preferred recommendations. Therefore, this paper proposes failure recovery solution for recommender systems with an adaptive filter. On the one hand, the proposed solution can deal with the failed recommendations while keeping the user engagement. Additionally, it allows the recommender system to dynamically fine tune the preferred items and become a long-term application. Also, the adaptive filter can avoid the cost of constantly updating the recommender learning model.

Citovat

BLANCO SÁNCHEZ, José Miguel, Mouzhi GE a Tomáš PITNER. An Adaptive Filter for Preference Fine-Tuning in Recommender Systems. Online. In 978-3-031-24197-0. WEB INFORMATION SYSTEMS AND TECHNOLOGIES, WEBIST 2020, WEBIST 2021. CHAM: SPRINGER INTERNATIONAL PUBLISHING AG, 2023, s. 107-121. ISBN 978-3-031-24196-3. Dostupné z: https://dx.doi.org/10.1007/978-3-031-24197-0_7.

@inproceedings{2392319,
   author = {Blanco Sánchez, José Miguel and Ge, Mouzhi and Pitner, Tomáš},
   address = {CHAM},
   booktitle = {WEB INFORMATION SYSTEMS AND TECHNOLOGIES, WEBIST 2020, WEBIST 2021},
   doi = {http://dx.doi.org/10.1007/978-3-031-24197-0_7},
   editor = {978-3-031-24197-0},
   keywords = {Recommender systems; Recommendation recovery; Adaptive filter; User-oriented recommendation},
   howpublished = {elektronická verze "online"},
   language = {eng},
   location = {CHAM},
   isbn = {978-3-031-24196-3},
   pages = {107-121},
   publisher = {SPRINGER INTERNATIONAL PUBLISHING AG},
   title = {An Adaptive Filter for Preference Fine-Tuning in Recommender Systems},
   year = {2023}
}

TY  - JOUR
ID  - 2392319
AU  - Blanco Sánchez, José Miguel - Ge, Mouzhi - Pitner, Tomáš
PY  - 2023
TI  - An Adaptive Filter for Preference Fine-Tuning in Recommender Systems
PB  - SPRINGER INTERNATIONAL PUBLISHING AG
CY  - CHAM
SN  - 9783031241963
KW  - Recommender systems
KW  - Recommendation recovery
KW  - Adaptive filter
KW  - User-oriented recommendation
N2  - A recommender system may recommend certain items that the users would not prefer. This can be caused by either the imperfection of the recommender system or the change of user preferences. When those failed recommendations appear often in the system, the users may consider that the recommender system is not able to capture the user preference. This can result in abandoning to further use the recommender system. However, given the possible failed recommendations, most recommender systems will ignore the non-preferred recommendations. Therefore, this paper proposes failure recovery solution for recommender systems with an adaptive filter. On the one hand, the proposed solution can deal with the failed recommendations while keeping the user engagement. Additionally, it allows the recommender system to dynamically fine tune the preferred items and become a long-term application. Also, the adaptive filter can avoid the cost of constantly updating the recommender learning model.
ER  -

BLANCO SÁNCHEZ, José Miguel, Mouzhi GE a Tomáš PITNER. An Adaptive Filter for Preference Fine-Tuning in Recommender Systems. Online. In 978-3-031-24197-0. \textit{WEB INFORMATION SYSTEMS AND TECHNOLOGIES, WEBIST 2020, WEBIST 2021}. CHAM: SPRINGER INTERNATIONAL PUBLISHING AG, 2023, s.~107-121. ISBN~978-3-031-24196-3. Dostupné z: https://dx.doi.org/10.1007/978-3-031-24197-0\_{}7.

Podrobný výpis o publikaci