An Improved Recommender System Solution to Mitigate the Over-Specialization Problem Using Genetic Algorithms
Nowadays, recommendation systems offer a method of facilitating the user’s desire. It is useful for recommending items from a variety of areas such as in the e-commerce, medical, education, tourism, and industry domains. The e-commerce area represents the most active research we found, which assists...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-01-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/11/2/242 |
| _version_ | 1797494540199788544 |
|---|---|
| author | Oumaima Stitini Soulaimane Kaloun Omar Bencharef |
| author_facet | Oumaima Stitini Soulaimane Kaloun Omar Bencharef |
| author_sort | Oumaima Stitini |
| collection | DOAJ |
| description | Nowadays, recommendation systems offer a method of facilitating the user’s desire. It is useful for recommending items from a variety of areas such as in the e-commerce, medical, education, tourism, and industry domains. The e-commerce area represents the most active research we found, which assists users in locating the things they want. A recommender system can also provide users with helpful knowledge about things that could be of interest. Sometimes, the user gets bored with recommendations which are similar to their profiles, which leads to the over-specialization problem. Over-specialization is caused by limited content data, under which content-based recommendation algorithms suggest goods directly related to the customer profile rather than new things. In this study, we are particularly interested in recommending surprising, new, and unexpected items that may likely be enjoyed by users and will mitigate this limited content. In order to recommend novel and serendipitous items along with familiar items, we need to introduce additional hacks and note of randomness, which can be achieved using genetic algorithms that brings diversity to recommendations being made. This paper describes a <b>R</b>evolutionary <b>R</b>ecommender <b>S</b>ystem using a <b>G</b>enetic <b>A</b>lgorithm called <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msub><mrow><mi mathvariant="bold-italic">R</mi><mi mathvariant="bold-italic">R</mi><mi mathvariant="bold-italic">S</mi></mrow><mrow><mi mathvariant="bold-italic">G</mi><mi mathvariant="bold-italic">A</mi></mrow></msub></semantics></math></inline-formula> which improves the fitness functions for recommending optimal results. The proposed approach employs a genetic algorithm to address the over-specialization issue of content-based filtering. The proposed method aims to incorporate genetic algorithms that bring variety to recommendations and efficiently adjust and suggest unpredictable and innovative things to the user. Experiments objectively demonstrate that our technology can recommend additional products that every consumer is likely to appreciate. The results of <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msub><mrow><mi mathvariant="bold-italic">R</mi><mi mathvariant="bold-italic">R</mi><mi mathvariant="bold-italic">S</mi></mrow><mrow><mi mathvariant="bold-italic">G</mi><mi mathvariant="bold-italic">A</mi></mrow></msub></semantics></math></inline-formula> have been compared against recommendation results from the content-based filtering approach. The results indicate the effectiveness of <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msub><mrow><mi mathvariant="bold-italic">R</mi><mi mathvariant="bold-italic">R</mi><mi mathvariant="bold-italic">S</mi></mrow><mrow><mi mathvariant="bold-italic">G</mi><mi mathvariant="bold-italic">A</mi></mrow></msub></semantics></math></inline-formula> and its capacity to make more accurate predictions than alternative approaches. |
| first_indexed | 2024-03-10T01:35:46Z |
| format | Article |
| id | doaj.art-b5f857a445f6432e8d7d001e397a5050 |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-10T01:35:46Z |
| publishDate | 2022-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-b5f857a445f6432e8d7d001e397a50502023-11-23T13:34:36ZengMDPI AGElectronics2079-92922022-01-0111224210.3390/electronics11020242An Improved Recommender System Solution to Mitigate the Over-Specialization Problem Using Genetic AlgorithmsOumaima Stitini0Soulaimane Kaloun1Omar Bencharef2Computer and System Engineering Laboratory, Faculty of Science and Technology, Cadi Ayyad University, Marrakech 40000, MoroccoComputer and System Engineering Laboratory, Faculty of Science and Technology, Cadi Ayyad University, Marrakech 40000, MoroccoComputer and System Engineering Laboratory, Faculty of Science and Technology, Cadi Ayyad University, Marrakech 40000, MoroccoNowadays, recommendation systems offer a method of facilitating the user’s desire. It is useful for recommending items from a variety of areas such as in the e-commerce, medical, education, tourism, and industry domains. The e-commerce area represents the most active research we found, which assists users in locating the things they want. A recommender system can also provide users with helpful knowledge about things that could be of interest. Sometimes, the user gets bored with recommendations which are similar to their profiles, which leads to the over-specialization problem. Over-specialization is caused by limited content data, under which content-based recommendation algorithms suggest goods directly related to the customer profile rather than new things. In this study, we are particularly interested in recommending surprising, new, and unexpected items that may likely be enjoyed by users and will mitigate this limited content. In order to recommend novel and serendipitous items along with familiar items, we need to introduce additional hacks and note of randomness, which can be achieved using genetic algorithms that brings diversity to recommendations being made. This paper describes a <b>R</b>evolutionary <b>R</b>ecommender <b>S</b>ystem using a <b>G</b>enetic <b>A</b>lgorithm called <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msub><mrow><mi mathvariant="bold-italic">R</mi><mi mathvariant="bold-italic">R</mi><mi mathvariant="bold-italic">S</mi></mrow><mrow><mi mathvariant="bold-italic">G</mi><mi mathvariant="bold-italic">A</mi></mrow></msub></semantics></math></inline-formula> which improves the fitness functions for recommending optimal results. The proposed approach employs a genetic algorithm to address the over-specialization issue of content-based filtering. The proposed method aims to incorporate genetic algorithms that bring variety to recommendations and efficiently adjust and suggest unpredictable and innovative things to the user. Experiments objectively demonstrate that our technology can recommend additional products that every consumer is likely to appreciate. The results of <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msub><mrow><mi mathvariant="bold-italic">R</mi><mi mathvariant="bold-italic">R</mi><mi mathvariant="bold-italic">S</mi></mrow><mrow><mi mathvariant="bold-italic">G</mi><mi mathvariant="bold-italic">A</mi></mrow></msub></semantics></math></inline-formula> have been compared against recommendation results from the content-based filtering approach. The results indicate the effectiveness of <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msub><mrow><mi mathvariant="bold-italic">R</mi><mi mathvariant="bold-italic">R</mi><mi mathvariant="bold-italic">S</mi></mrow><mrow><mi mathvariant="bold-italic">G</mi><mi mathvariant="bold-italic">A</mi></mrow></msub></semantics></math></inline-formula> and its capacity to make more accurate predictions than alternative approaches.https://www.mdpi.com/2079-9292/11/2/242genetic algorithmsrecommender systemover-specializationcontent-based filteringlimited content |
| spellingShingle | Oumaima Stitini Soulaimane Kaloun Omar Bencharef An Improved Recommender System Solution to Mitigate the Over-Specialization Problem Using Genetic Algorithms Electronics genetic algorithms recommender system over-specialization content-based filtering limited content |
| title | An Improved Recommender System Solution to Mitigate the Over-Specialization Problem Using Genetic Algorithms |
| title_full | An Improved Recommender System Solution to Mitigate the Over-Specialization Problem Using Genetic Algorithms |
| title_fullStr | An Improved Recommender System Solution to Mitigate the Over-Specialization Problem Using Genetic Algorithms |
| title_full_unstemmed | An Improved Recommender System Solution to Mitigate the Over-Specialization Problem Using Genetic Algorithms |
| title_short | An Improved Recommender System Solution to Mitigate the Over-Specialization Problem Using Genetic Algorithms |
| title_sort | improved recommender system solution to mitigate the over specialization problem using genetic algorithms |
| topic | genetic algorithms recommender system over-specialization content-based filtering limited content |
| url | https://www.mdpi.com/2079-9292/11/2/242 |
| work_keys_str_mv | AT oumaimastitini animprovedrecommendersystemsolutiontomitigatetheoverspecializationproblemusinggeneticalgorithms AT soulaimanekaloun animprovedrecommendersystemsolutiontomitigatetheoverspecializationproblemusinggeneticalgorithms AT omarbencharef animprovedrecommendersystemsolutiontomitigatetheoverspecializationproblemusinggeneticalgorithms AT oumaimastitini improvedrecommendersystemsolutiontomitigatetheoverspecializationproblemusinggeneticalgorithms AT soulaimanekaloun improvedrecommendersystemsolutiontomitigatetheoverspecializationproblemusinggeneticalgorithms AT omarbencharef improvedrecommendersystemsolutiontomitigatetheoverspecializationproblemusinggeneticalgorithms |