Learning Representations of Hierarchical Slates in Collaborative Filtering

Elahi, Ehtsham; Chandrashekar, Ashok

doi:10.48550/arxiv.2010.06987

Cited by 1 publication

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A recent work from Netflix [8] presented a method to recommend existing collections. That is, given a set of collections already available, the method predicts the ratings of the collections (𝑅 𝑢 ) as well as the ratings of the items (𝑟 𝑢 ) within a collection w.r.t.…”

Section: Automatic Collection Recommendationmentioning

confidence: 99%

See 1 more Smart Citation

Automatic Collection Creation and Recommendation

Singal¹,

Singh²,

Dahiya³

2021

Preprint

View full text Add to dashboard Cite

We present a collection recommender system that can automatically create and recommend collections of items at a user level. Unlike regular recommender systems, which output top-N relevant items, a collection recommender system outputs collections of items such that the items in the collections are relevant to a user, and the items within a collection follow a specific theme. Our system builds on top of the user-item representations learnt by item recommender systems. We employ dimensionality reduction and clustering techniques along with intuitive heuristics to create collections with their ratings and titles.We test these ideas in a real-world setting of music recommendation, within a popular music streaming service. We find that there is a 2.3x increase in recommendation-driven consumption when recommending collections over items. Further, it results in effective utilization of real estate and leads to recommending a more and diverse set of items. To our knowledge, these are first of its kind experiments at such a large scale.

show abstract

Section: Automatic Collection Recommendationmentioning

confidence: 99%

“…Collection recommendation aptly fits the domain of music, and it has wider applications. For example, in movie recommendation, we need to recommend personalized collections based on specific genres such as thriller and comedy [8,12]. In case of e-commerce, collections are recommended based on the product categories [20].…”

Section: Introductionmentioning

confidence: 99%