Proceedings of the ACM Recommender Systems Challenge 2018最新文献_第2页

Artist-driven layering and user's behaviour impact on recommendations in a playlist continuation scenario 艺术家驱动的分层和用户行为影响播放列表延续场景中的推荐

Proceedings of the ACM Recommender Systems Challenge 2018 Pub Date : 2018-10-02 DOI: 10.1145/3267471.3267475

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

引用次数: 18

Automatic Playlist Continuation using Subprofile-Aware Diversification 使用子配置文件感知多样化自动播放列表延续

Proceedings of the ACM Recommender Systems Challenge 2018 Pub Date : 2018-10-02 DOI: 10.1145/3267471.3267472

Mesut Kaya, D. Bridge

引用次数: 8

Two-stage Model for Automatic Playlist Continuation at Scale 大规模自动播放列表延续的两阶段模型

Proceedings of the ACM Recommender Systems Challenge 2018 Pub Date : 2018-10-02 DOI: 10.1145/3267471.3267480

M. Volkovs, Himanshu Rai, Zhaoyue Cheng, Ga Wu, Y. Lu, S. Sanner

引用次数: 35

Automatic Music Playlist Continuation via Neighbor-based Collaborative Filtering and Discriminative Reweighting/Reranking 基于邻域协同过滤和判别性重加权/重排序的音乐播放列表自动延续

Proceedings of the ACM Recommender Systems Challenge 2018 Pub Date : 2018-10-02 DOI: 10.1145/3267471.3267481

Lin Zhu, Bowen He, Mengxin Ji, Cheng Ju, Yihong Chen

{"title":"Automatic Music Playlist Continuation via Neighbor-based Collaborative Filtering and Discriminative Reweighting/Reranking","authors":"Lin Zhu, Bowen He, Mengxin Ji, Cheng Ju, Yihong Chen","doi":"10.1145/3267471.3267481","DOIUrl":"https://doi.org/10.1145/3267471.3267481","url":null,"abstract":"The focus of RecSys Challenge 2018 is automatic playlist continuation (APC), which refers to the task of adding one or more tracks to a playlist in a manner that does not alter the intended characteristics of the original playlist. This paper presents our approach to this challenge. We adopted neighbor-based collaborative filtering approaches since they are able to deal with large datasets in an efficient and effective way, and have previously been shown to perform well on recommendation problems with similar characteristics. We show that by choosing an appropriate similarity function that properly accounts for the list-song similarities, simple neighbor-based methods can still achieve highly competitive performance on the MPD data, meanwhile, by using a set of techniques that discriminantly finetune the recommendation lists produced by neighbor-based methods, the overall recommendation accuracy can be improved significantly. By using the proposed approach, our team HAIR was able to attain the 6th place in the competition. We have open-sourced our implementation on https://github.com/LauraBowenHe/Recsys-Spotify-2018-challenge.","PeriodicalId":430663,"journal":{"name":"Proceedings of the ACM Recommender Systems Challenge 2018","volume":"431 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116009113","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 5

A Line in the Sand: Recommendation or Ad-hoc Retrieval? Overview of RecSys Challenge 2018 Submission by Team BachPropagate 底线:推荐还是临时检索?BachPropagate团队提交的RecSys挑战赛2018概述

Proceedings of the ACM Recommender Systems Challenge 2018 Pub Date : 2018-07-21 DOI: 10.1145/3267471.3267478

S. Kallumadi, Bhaskar Mitra, Tereza Iofciu

{"title":"A Line in the Sand: Recommendation or Ad-hoc Retrieval? Overview of RecSys Challenge 2018 Submission by Team BachPropagate","authors":"S. Kallumadi, Bhaskar Mitra, Tereza Iofciu","doi":"10.1145/3267471.3267478","DOIUrl":"https://doi.org/10.1145/3267471.3267478","url":null,"abstract":"The popular approaches to recommendation and ad-hoc retrieval tasks are largely distinct in the literature. In this work, we argue that many recommendation problems can also be cast as ad-hoc retrieval tasks. To demonstrate this, we build a solution for the RecSys 2018 Spotify challenge by combining standard ad-hoc retrieval models and using popular retrieval tools sets. We draw a parallel between the playlist continuation task and the task of finding good expansion terms for queries in ad-hoc retrieval, and show that standard pseudo-relevance feedback can be effective as a collaborative filtering approach. We also use ad-hoc retrieval for content-based recommendation by treating the input playlist title as a query and associating all candidate tracks with meta-descriptions extracted from the background data. The recommendations from these two approaches are further supplemented by a nearest neighbor search based on track embeddings learned by a popular neural model. Our final ranked list of recommendations is produced by a learning to rank model. Our proposed solution using ad-hoc retrieval models achieved a competitive performance on the music recommendation task at RecSys 2018 challenge---finishing at rank 7 out of 112 participating teams and at rank 5 out of 31 teams for the main and the creative tracks, respectively.","PeriodicalId":430663,"journal":{"name":"Proceedings of the ACM Recommender Systems Challenge 2018","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129474785","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 7