Automated Playlist Continuation with Apache PredictionIO
The Minrva project team, a software development research group based at the University of Illinois Library, developed a data-focused recommender system to participate in the creative track of the 2018 ACM RecSys Challenge, which focused on music recommendation. We describe here the large-scale data...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Code4Lib
2018-11-01
|
| Series: | Code4Lib Journal |
| Online Access: | https://journal.code4lib.org/articles/13850 |
| _version_ | 1811222785523974144 |
|---|---|
| author | Jim Hahn |
| author_facet | Jim Hahn |
| author_sort | Jim Hahn |
| collection | DOAJ |
| description | The Minrva project team, a software development research group based at the University of Illinois Library, developed a data-focused recommender system to participate in the creative track of the 2018 ACM RecSys Challenge, which focused on music recommendation. We describe here the large-scale data processing the Minrva team researched and developed for foundational reconciliation of the Million Playlist Dataset using external authority data on the web (e.g. VIAF, WikiData). The secondary focus of the research was evaluating and adapting the processing tools that support data reconciliation. This paper reports on the playlist enrichment process, indexing, and subsequent recommendation model developed for the music recommendation challenge. |
| first_indexed | 2024-04-12T08:21:21Z |
| format | Article |
| id | doaj.art-c7d28e2f8c794a119af0bec222efe483 |
| institution | Directory Open Access Journal |
| issn | 1940-5758 |
| language | English |
| last_indexed | 2024-04-12T08:21:21Z |
| publishDate | 2018-11-01 |
| publisher | Code4Lib |
| record_format | Article |
| series | Code4Lib Journal |
| spelling | doaj.art-c7d28e2f8c794a119af0bec222efe4832022-12-22T03:40:34ZengCode4LibCode4Lib Journal1940-57582018-11-014213850Automated Playlist Continuation with Apache PredictionIOJim HahnThe Minrva project team, a software development research group based at the University of Illinois Library, developed a data-focused recommender system to participate in the creative track of the 2018 ACM RecSys Challenge, which focused on music recommendation. We describe here the large-scale data processing the Minrva team researched and developed for foundational reconciliation of the Million Playlist Dataset using external authority data on the web (e.g. VIAF, WikiData). The secondary focus of the research was evaluating and adapting the processing tools that support data reconciliation. This paper reports on the playlist enrichment process, indexing, and subsequent recommendation model developed for the music recommendation challenge.https://journal.code4lib.org/articles/13850 |
| spellingShingle | Jim Hahn Automated Playlist Continuation with Apache PredictionIO Code4Lib Journal |
| title | Automated Playlist Continuation with Apache PredictionIO |
| title_full | Automated Playlist Continuation with Apache PredictionIO |
| title_fullStr | Automated Playlist Continuation with Apache PredictionIO |
| title_full_unstemmed | Automated Playlist Continuation with Apache PredictionIO |
| title_short | Automated Playlist Continuation with Apache PredictionIO |
| title_sort | automated playlist continuation with apache predictionio |
| url | https://journal.code4lib.org/articles/13850 |
| work_keys_str_mv | AT jimhahn automatedplaylistcontinuationwithapachepredictionio |