Large-scale user modeling with recurrent neural networks for music discovery on multiple time scales

Abstract

The amount of content on online music streaming platforms is immense, and most users only access a tiny fraction of this content. Recommender systems are the application of choice to open up the collection to these users. Collaborative filtering has the disadvantage that it relies on explicit ratings, which are often unavailable, and generally disregards the temporal nature of music consumption. On the other hand, item co-occurrence algorithms, such as the recently introduced word2vec-based recommenders, are typically left without an effective user representation. In this paper, we present a new approach to model users through recurrent neural networks by sequentially processing consumed items, represented by any type of embeddings and other context features. This way we obtain semantically rich user representations, which capture a user's musical taste over time. Our experimental analysis on large-scale user data shows that our model can be used to predict future songs a user will likely listen to, both in the short and long term

Attention-based mixture density recurrent networks for history-based recommendation

“…The major difference between the proposed work and the work by De Boom et al (2017) is the assumption on the number of modes in the distribution of user behaviors. The proposed model considers the mapping from history to a future behaviour as a probability distribution with multiple modes, unlike their work in which such a distribution is assumed to be unimodal.…”

Deep neural network marketplace recommenders in online experiments

“…Moreover, models of cascade [16] or sequential attention [22] that consider a longer user behavior history show particularly good results. Our sequential recommender draws inspiration from [2] and shows positive performance improvements in online experiments. Multi-armed bandits for prioritizing among multiple sources is applied in different use cases.…”

Character-level recurrent neural networks in practice: comparing training and sampling schemes

“…To help the RNN model long-term dependencies and to counter the vanishing gradient problem [15], several extensions on Equation (6) have been proposed. The best known examples are long short-term memories (LSTMs) and, more recently, gated recurrent units (GRUs), which both have comparable characteristics and similar performance on a variety of tasks [4,10,16].…”

“…Author communication [1] Word-level 4 (?) Author communication (Zoph, 2016) [43] Word-level 4 Author communication (Inan, 2016) [18] Word-level 4 Source code (Merity, 2017) [25] Word-level 4 Source code (Yang, 2017) [40] Word-level 3 Author communication (Sturm, 2016) [35] Music notes 3 Author communication (Saon, 2016) [32] Phonemes 3 Author communication (De Boom, 2017) [6] Playlist tracks 2 Paper…”