Artist-driven layering and user's behaviour impact on recommendations in a playlist continuation scenario

Antenucci, Sebastiano; Boglio, Simone; Chioso, Emanuele; Dervishaj, Ervin; Kang, Shuwen; Scarlatti, Tommaso; Dacrema, Maurizio Ferrari

doi:10.1145/3267471.3267475

Cited by 22 publications

(23 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Specifically, we included long papers in our analysis that appeared between 2015 and 2018 in the following four conference series: KDD, SIGIR, TheWebConf (WWW), and RecSys. 1 We considered a paper to be relevant if it (a) proposed a deep learning based technique and (b) focused on the top-n recommendation problem. Papers on other recommendation tasks, e.g., group recommendation or session-based recommendation, were not considered in our analysis.…”

Section: Research Methods 21 Collecting Reproducible Papersmentioning

confidence: 99%

See 1 more Smart Citation

Are we really making much progress? A worrying analysis of recent neural recommendation approaches

Dacrema

Cremonesi

Jannach

2019

Proceedings of the 13th ACM Conference on Recommender Systems

Self Cite

430

166

View full text Add to dashboard Cite

Deep learning techniques have become the method of choice for researchers working on algorithmic aspects of recommender systems. With the strongly increased interest in machine learning in general, it has, as a result, become difficult to keep track of what represents the state-of-the-art at the moment, e.g., for top-n recommendation tasks. At the same time, several recent publications point out problems in today's research practice in applied machine learning, e.g., in terms of the reproducibility of the results or the choice of the baselines when proposing new models.In this work, we report the results of a systematic analysis of algorithmic proposals for top-n recommendation tasks. Specifically, we considered 18 algorithms that were presented at top-level research conferences in the last years. Only 7 of them could be reproduced with reasonable effort. For these methods, it however turned out that 6 of them can often be outperformed with comparably simple heuristic methods, e.g., based on nearest-neighbor or graph-based techniques. The remaining one clearly outperformed the baselines but did not consistently outperform a well-tuned nonneural linear ranking method. Overall, our work sheds light on a number of potential problems in today's machine learning scholarship and calls for improved scientific practices in this area.

show abstract

Section: Research Methods 21 Collecting Reproducible Papersmentioning

confidence: 99%

“…For all baseline algorithms and datasets, we determined the optimal parameters via Bayesian search [1] using the implementation of Scikit-Optimize 6 . We explored 35 cases for each algorithm, where the first 5 were used for the initial random points.…”

Section: Evaluation Methodologymentioning

confidence: 99%

Are we really making much progress? A worrying analysis of recent neural recommendation approaches

Dacrema

Cremonesi

Jannach

2019

Proceedings of the 13th ACM Conference on Recommender Systems

Self Cite

430

166

View full text Add to dashboard Cite

show abstract

“…Secondly, the tuning of the hyper-parameters of the feature weighting machine learning is performed in a similar way, again optimizing MAP. We searched the optimal hyper-parameters via a Bayesian search (Antenucci et al 2018) using the implementation of Scickitoptimize. 13 As for different aggregation methods designed for the audio and visual features, we chose the best performing ones with regards to the metric under study.…”

Section: Hyper-parameter Tuningmentioning

confidence: 99%

Movie genome: alleviating new item cold start in movie recommendation

Deldjoo

Dacrema

Constantin

et al. 2019

User Model User-Adap Inter

View full text Add to dashboard Cite

As of today, most movie recommendation services base their recommendations on collaborative filtering (CF) and/or content-based filtering (CBF) models that use metadata (e.g., genre or cast). In most video-on-demand and streaming services, however, new movies and TV series are continuously added. CF models are unable to make predictions in such a scenario, since the newly added videos lack interactions-a problem technically known as new item cold start (CS). Currently, the most common approach to this problem is to switch to a purely CBF method, usually by exploiting textual metadata. This approach is known to have lower accuracy than CF because it ignores useful collaborative information and relies on human-generated textual metadata, which are expensive to collect and often prone to errors. User-generated content, such as tags, can also be rare or absent in CS situations. In this paper, we introduce a new movie recommender system that addresses the new item problem in the movie domain by (i) integrating state-of-the-art audio and visual descriptors, which can be automatically extracted from video content and constitute what we call the movie genome; (ii) exploiting an effective data fusion method named canonical correlation analysis, which was successfully tested in our previous works Deldjoo et alto better exploit complementary information between different modalities; (iii) proposing a two-step hybrid approach which trains a CF model on warm items (items with interactions) and leverages the learned model on the movie genome to recommend cold items (items without interactions). Experimental validation is carried out using a system-centric study on a large-scale, real-world movie recommendation dataset both in an absolute cold start and in a cold to warm transition; and a user-centric online experiment measuring different subjective aspects, such as satisfaction and diversity. Results show the benefits of this approach compared to existing approaches.

show abstract

“…For each model we report in Table 1 the best MRR achieved on the private validation dataset. The hyperparameters tuning is done via Random and Bayesian search [2,4,5].…”

Section: Experimental Evaluationmentioning

confidence: 99%

“…We publicly release our source code with additional documentation and information on our solution. 2…”

Section: Introductionmentioning

confidence: 99%

Leveraging laziness, browsing-pattern aware stacked models for sequential accommodation learning to rank

D’Amico

Gabbolini

Montesi

et al. 2019

Proceedings of the Workshop on ACM Recommender Systems Challenge

Self Cite

View full text Add to dashboard Cite

In this paper we provide an overview of the approach we used as team PoliCloud8 for the ACM RecSys Challenge 2019. The competition, organized by Trivago, focuses on the problem of session-based and context-aware accommodation recommendation in a travel domain. The goal is to suggest suitable accommodations fitting the needs of the traveller to maximise the chance of a redirect (clickout) to a booking site, relying on explicit and implicit user signals within a session (clicks, search refinement, filter usage) to detect the users intent. Our team proposes a solution based on several new features, designed to capture specific types of information as well as some well-known models: gradient boosting, neural networks and a stacking-based ensemble.

show abstract

Artist-driven layering and user's behaviour impact on recommendations in a playlist continuation scenario

Cited by 22 publications

References 8 publications

Are we really making much progress? A worrying analysis of recent neural recommendation approaches

Are we really making much progress? A worrying analysis of recent neural recommendation approaches

Movie genome: alleviating new item cold start in movie recommendation

Leveraging laziness, browsing-pattern aware stacked models for sequential accommodation learning to rank

Contact Info

Product

Resources

About