Off-line vs. On-line Evaluation of Recommender Systems in Small E-commerce

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F20%3A10416944" target="_blank" >RIV/00216208:11320/20:10416944 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.1145/3372923.3404781" target="_blank" >https://doi.org/10.1145/3372923.3404781</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1145/3372923.3404781" target="_blank" >10.1145/3372923.3404781</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Off-line vs. On-line Evaluation of Recommender Systems in Small E-commerce

Popis výsledku v původním jazyce

In this paper, we present our work towards comparing on-line and off-line evaluation metrics in the context of small e-commerce recommender systems. Recommending on small e-commerce enterprises is rather challenging due to the lower volume of interactions and low user loyalty, rarely extending beyond a single session. On the other hand, we usually have to deal with lower volumes of objects, which are easier to discover by users through various browsing/searching GUIs. The main goal of this paper is to determine applicability of off-line evaluation metrics in learning true usability of recommender systems (evaluated on-line in A/B testing). In total 800 variants of recommenders were evaluated off-line w.r.t. 18 metrics covering rating-based, ranking-based, novelty and diversity evaluation. The off-line results were afterwards compared with on-line evaluation of 12 selected recommender variants and based on the results, we tried to learn and utilize an off-line to on-line results prediction model. Off-line results shown a great variance in performance w.r.t. different metrics with the Pareto front covering 64% of the approaches. Furthermore, we observed that on-line results are considerably affected by the seniority of users. On-line metrics correlates positively with ranking-based metrics (AUC, MRR, nDCG) for novice users, while too high values of novelty had a negative impact on the on-line results for them.

Název v anglickém jazyce

Off-line vs. On-line Evaluation of Recommender Systems in Small E-commerce

Popis výsledku anglicky

In this paper, we present our work towards comparing on-line and off-line evaluation metrics in the context of small e-commerce recommender systems. Recommending on small e-commerce enterprises is rather challenging due to the lower volume of interactions and low user loyalty, rarely extending beyond a single session. On the other hand, we usually have to deal with lower volumes of objects, which are easier to discover by users through various browsing/searching GUIs. The main goal of this paper is to determine applicability of off-line evaluation metrics in learning true usability of recommender systems (evaluated on-line in A/B testing). In total 800 variants of recommenders were evaluated off-line w.r.t. 18 metrics covering rating-based, ranking-based, novelty and diversity evaluation. The off-line results were afterwards compared with on-line evaluation of 12 selected recommender variants and based on the results, we tried to learn and utilize an off-line to on-line results prediction model. Off-line results shown a great variance in performance w.r.t. different metrics with the Pareto front covering 64% of the approaches. Furthermore, we observed that on-line results are considerably affected by the seniority of users. On-line metrics correlates positively with ranking-based metrics (AUC, MRR, nDCG) for novice users, while too high values of novelty had a negative impact on the on-line results for them.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

<a href="/cs/project/GJ19-22071Y" target="_blank" >GJ19-22071Y: Flexibilní modely pro hledání známé scény v rozsáhlých kolekcích videa</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2020

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Proceedings of the 31st ACM Conference on Hypertext and Social Media

ISBN

978-1-4503-7098-1

ISSN

—

e-ISSN

—

Počet stran výsledku

10

Strana od-do

291-300

Název nakladatele

ACM

Místo vydání

New York, USA

Místo konání akce

Virtual Event, USA

Datum konání akce

13. 7. 2020

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—