A Bandit-Based Ensemble Framework for Exploration/Exploitation of Diverse Recommendation Components: An Experimental Study within E-Commerce

A Bandit-Based Ensemble Framework for Exploration/Exploitation of Diverse Recommendation Components : An Experimental Study within E-Commerce

Brodén, Björn (author): Apptus Technologies, Trollebergsvägen 5, Lund, 22229, Sweden

Hammar, Mikael (author): Apptus Technologies, Trollebergsvägen 5, Lund, 22229, Sweden

Nilsson, Bengt J. (author): Malmö universitet,Institutionen för datavetenskap och medieteknik (DVMT)

Paraschakis, Dimitris (author): Malmö universitet,Institutionen för datavetenskap och medieteknik (DVMT)

(creator_code:org_t)

2019-08-09
2019
English.
In: ACM Transactions on Interactive Intelligent Systems. - : ACM Digital Library. - 2160-6455 .- 2160-6463. ; 10:1, s. 4:1-4:32

Related links:: https://urn.kb.se/re...; show more...; https://doi.org/10.1...; show less...

Abstract Subject headings

This work presents an extension of Thompson Sampling bandit policy for orchestrating the collection of base recommendation algorithms for e-commerce. We focus on the problem of item-to-item recommendations, for which multiple behavioral and attribute-based predictors are provided to an ensemble learner. In addition, we detail the construction of a personalized predictor based on k-Nearest Neighbors (kNN), with temporal decay capabilities and event weighting. We show how to adapt Thompson Sampling to realistic situations when neither action availability nor reward stationarity is guaranteed. Furthermore, we investigate the effects of priming the sampler with pre-set parameters of reward probability distributions by utilizing the product catalog and/or event history, when such information is available. We report our experimental results based on the analysis of three real-world e-commerce datasets.

By the author/editor: Brodén, Björn; Hammar, Mikael; Nilsson, Bengt J ...; Paraschakis, Dim ...

About the subject

ENGINEERING AND TECHNOLOGY: ENGINEERING AND ...; and Civil Engineerin ...; and Transport System ...

Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.