MovieDIRec: Drafted-Input-Based Recommendation System for Movies
In a DNN-based recommendation system, the input selection of a model and design of an appropriate input are very important in terms of the accuracy and reflection of complex user preferences. Since the learning of layers by the goal of the model depends on the input, the more closely the input is re...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-11-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/11/21/10412 |
| _version_ | 1827600608046088192 |
|---|---|
| author | Hyeonwoo An Daeyeol Kim Kwangkee Lee Nammee Moon |
| author_facet | Hyeonwoo An Daeyeol Kim Kwangkee Lee Nammee Moon |
| author_sort | Hyeonwoo An |
| collection | DOAJ |
| description | In a DNN-based recommendation system, the input selection of a model and design of an appropriate input are very important in terms of the accuracy and reflection of complex user preferences. Since the learning of layers by the goal of the model depends on the input, the more closely the input is related to the goal, the less the model needs to learn unnecessary information. In relation to this, the term Drafted-Input, defined in this paper, is input data that have been appropriately selected and processed to meet the goals of the system, and is a subject that is updated while continuously reflecting user preferences along with the learning of model parameters. In this paper, the effects of properly designed and generated inputs on accuracy and usability are verified using the proposed systems. Furthermore, the proposed method and user–item interaction are compared with state-of-the-art systems using simple embedding data as the input, and a model suitable for a practical client–server environment is also proposed. |
| first_indexed | 2024-03-09T04:39:35Z |
| format | Article |
| id | doaj.art-f5cbe709ee1240ce80582c6cb6a6ed3b |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-09T04:39:35Z |
| publishDate | 2021-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-f5cbe709ee1240ce80582c6cb6a6ed3b2023-12-03T13:23:32ZengMDPI AGApplied Sciences2076-34172021-11-0111211041210.3390/app112110412MovieDIRec: Drafted-Input-Based Recommendation System for MoviesHyeonwoo An0Daeyeol Kim1Kwangkee Lee2Nammee Moon3Tvstorm, Sunghyun Building, 255 Hyorung-ro, Secho-gu, Seoul 13875, KoreaTvstorm, Sunghyun Building, 255 Hyorung-ro, Secho-gu, Seoul 13875, KoreaTvstorm, Sunghyun Building, 255 Hyorung-ro, Secho-gu, Seoul 13875, KoreaDepartment of Computer Engineering, Hoseo University, Asan 31499, KoreaIn a DNN-based recommendation system, the input selection of a model and design of an appropriate input are very important in terms of the accuracy and reflection of complex user preferences. Since the learning of layers by the goal of the model depends on the input, the more closely the input is related to the goal, the less the model needs to learn unnecessary information. In relation to this, the term Drafted-Input, defined in this paper, is input data that have been appropriately selected and processed to meet the goals of the system, and is a subject that is updated while continuously reflecting user preferences along with the learning of model parameters. In this paper, the effects of properly designed and generated inputs on accuracy and usability are verified using the proposed systems. Furthermore, the proposed method and user–item interaction are compared with state-of-the-art systems using simple embedding data as the input, and a model suitable for a practical client–server environment is also proposed.https://www.mdpi.com/2076-3417/11/21/10412MovieDIRecdrafted-inputpersonalized recommendation system |
| spellingShingle | Hyeonwoo An Daeyeol Kim Kwangkee Lee Nammee Moon MovieDIRec: Drafted-Input-Based Recommendation System for Movies Applied Sciences MovieDIRec drafted-input personalized recommendation system |
| title | MovieDIRec: Drafted-Input-Based Recommendation System for Movies |
| title_full | MovieDIRec: Drafted-Input-Based Recommendation System for Movies |
| title_fullStr | MovieDIRec: Drafted-Input-Based Recommendation System for Movies |
| title_full_unstemmed | MovieDIRec: Drafted-Input-Based Recommendation System for Movies |
| title_short | MovieDIRec: Drafted-Input-Based Recommendation System for Movies |
| title_sort | moviedirec drafted input based recommendation system for movies |
| topic | MovieDIRec drafted-input personalized recommendation system |
| url | https://www.mdpi.com/2076-3417/11/21/10412 |
| work_keys_str_mv | AT hyeonwooan moviedirecdraftedinputbasedrecommendationsystemformovies AT daeyeolkim moviedirecdraftedinputbasedrecommendationsystemformovies AT kwangkeelee moviedirecdraftedinputbasedrecommendationsystemformovies AT nammeemoon moviedirecdraftedinputbasedrecommendationsystemformovies |