Please use this identifier to cite or link to this item:
https://dspace.univ-ouargla.dz/jspui/handle/123456789/36825
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | Mohamed El-Amine Abderrahim | - |
dc.contributor.author | Beddouda, Amira Riham | - |
dc.contributor.author | Belhemissi, Bochra | - |
dc.date.accessioned | 2024-09-24T08:45:08Z | - |
dc.date.available | 2024-09-24T08:45:08Z | - |
dc.date.issued | 2024 | - |
dc.identifier.citation | FACULTY OF N EW I NFORMATION AND C OMMUNICATION T ECHNOLOGIES | en_US |
dc.identifier.uri | https://dspace.univ-ouargla.dz/jspui/handle/123456789/36825 | - |
dc.description | Artificial Intelligence and Data Science | en_US |
dc.description.abstract | The study explores the integration of the BERT4Rec model, a Natural Language Processing (NLP) model, into recommendation systems for the used automobile market. The model aims to improve user experience and sales by analyzing user preferences and past interactions. The study’s methodology includes feature encoding, data cleaning, sequence modeling prepara- tion, model training, and evaluation. The study aims to determine the effectiveness of the integrated BERT4Rec model in resolving the issue and enhancing recommendation accuracy within the used car market. Preliminary results show a 70% accuracy rate, indicating sig- nificant progress in recommendation systems. These findings could significantly impact the industry by improving user experiences and increasing sales in e-commerce platforms operating in the used automobile market. | en_US |
dc.description.abstract | ﺗﺴﺘﻜﺸﻒﺍﻟﺪﺭﺍﺳﺔ ﺩﻣﺞ ﻧﻤﻮﺫﺝ BERT4Rec ، ﻭﻫﻮ ﻧﻤﻮﺫﺝ ﻣﻌﺎﻟﺠﺔ ﺍﻟﻠﻐﺎﺕ ﻟﻄﺒﻴﻌﻴﺔ NLP، ﻓﻲ ﺃﻧﻈﻤﺔ ﺍﻟﺘﻮﺻﻴﺔ ﻟﺴﻮﻕ ﺍﻟﺴﻴﺎﺭﺍﺕ ﺍﻟﻤﺴﺘﻌﻤﻠﺔ. ﻳﻬﺪﻑ ﺍﻟﻨﻤﻮﺫﺝ ﺇﻟﻰ ﺗﺤﺴﻴﻦ ﺗﺠﺮﺑﺔﺍﻟﻤﺴﺘﺨﺪﻡ ﻭﺍﻟﻤﺒﻴﻌﺎﺕ ﻣﻦ ﺧﻼﻝ ﺗﺤﻠﻴﻞ ﺗﻔﻀﻴﻼﺕ ﺍﻟﻤﺴﺘﺨﺪﻡ ﻭﺍﻟﺘﻔﺎﻋﻼﺕ ﺍﻟﺴﺎﺑﻘﺔ. ﺗﺘﻀﻤﻦﻣﻨﻬﺠﻴﺔ ﺍﻟﺪﺭﺍﺳﺔ ﺗﺮﻣﻴﺰ ﺍﻟﻤﻴﺰﺍﺕ ﻭﺗﻨﻈﻴﻒ ﺍﻟﺒﻴﺎﻧﺎﺕ، ﻭﺇﻋﺪﺍﺩ ﻧﻤﺬﺟﺔ ﺍﻟﺘﺴﻠﺴﻞ، ﺗﻬﺪﻑﺍﻟﺪﺭﺍﺳﺔ ﺇﻟﻰ ﺗﺤﺪﻳﺪ ﻣﺪﻯ ﻓﻌﺎﻟﻴﺔ ﻧﻤﻮﺫﺝ ﻭﺍﻟﺘﺪﺭﻳﺐ ﻋﻠﻰ ﺍﻟﻨﻤﺎﺫﺝ، ﻭﺍﻟﺘﻘﻴﻴﻢ. BERT4Recﺍﻟﻤﺘﻜﺎﻣﻞ ﻓﻲ ﺣﻞ ﺍﻟﻤﺸﻜﻠﺔ ﻭﺗﻌﺰﻳﺰ ﺩﻗﺔ ﺍﻟﺘﻮﺻﻴﺎﺕ ﺩﺍﺧﻞ ﺳﻮﻕ ﺍﻟﺴﻴﺎﺭﺍﺕ ﺍﻟﻤﺴﺘﻌﻤﻠﺔ.ﻭﺗﻈﻬﺮ ﺍﻟﻨﺘﺎﺋﺞ ﺍﻷﻭﻟﻴﺔ ﻧﺴﺒﺔ ﺩﻗﺔ ﺗﺒﻠﻎ 70% ، ﻣﻤﺎ ﻳﺸﻴﺮ ﺇﻟﻰ ﺗﻘﺪﻡ ﻛﺒﻴﺮ ﻓﻲﺃﻧﻈﻤﺔ ﺍﻟﺘﻮﺻﻴﺔ. ﻳﻤﻜﻦ ﺃﻥ ﺗﺆﺛﺮ ﻫﺬﻩ ﺍﻟﻨﺘﺎﺋﺞ ﺑﺸﻜﻞ ﻛﺒﻴﺮ ﻋﻠﻰ ﺍﻟﺼﻨﺎﻋﺔ ﻣﻦ ﺧﻼﻝ ﺗﺤﺴﻴﻦﺗﺠﺎﺭﺏ ﺍﻟﻤﺴﺘﺨﺪﻡ ﻭﺯﻳﺎﺩﺓ ﺍﻟﻤﺒﻴﻌﺎﺕ ﻓﻲ ﻣﻨﺼﺎﺕ ﺍﻟﺘﺠﺎﺭﺓ ﺍﻹﻟﻜﺘﺮﻭﻧﻴﺔ ﺍﻟﻌﺎﻣﻠﺔ ﻓﻲ ﺳﻮﻕﺍﻟﺴﻴﺎﺭﺍﺕ ﺍﻟﻤﺴﺘﻌﻤﻠﺔ. | - |
dc.description.sponsorship | Department of Computer Science and Information Technology | en_US |
dc.language.iso | en | en_US |
dc.publisher | KASDI MERBAH UNIVERSITY OUARGLA | en_US |
dc.subject | BERT4Rec model | en_US |
dc.subject | Natural Language Processing (NLP) | en_US |
dc.subject | used automobile market | en_US |
dc.subject | user experience | en_US |
dc.title | A VEHICLE RECOMMENDATION SYSTEM FOR SALES | en_US |
dc.type | Thesis | en_US |
Appears in Collections: | Département d'informatique et technologie de l'information - Master |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
BEDDOUDA- BELHEMISSI.pdf | Artificial Intelligence and Data Science | 1,12 MB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.