M. Naufaldi Fadhlirrahman, . (2025) PERANCANGAN MODEL TWO-TOWER PADA SISTEM REKOMENDASI APLIKASI MARKETPLACE PASAR HASIL BUMI. Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.
![[img]](http://repository.upnvj.ac.id/style/images/fileicons/text.png) |
Text
ABSTRAK.pdf Download (2MB) |
|
Text
AWAL.pdf Download (2MB) |
|
Text
BAB 1.pdf Restricted to Repository UPNVJ Only Download (1MB) |
|
Text
BAB 2.pdf Restricted to Repository UPNVJ Only Download (1MB) |
|
Text
BAB 3.pdf Restricted to Repository UPNVJ Only Download (1MB) |
|
Text
BAB 4.pdf Restricted to Repository UPNVJ Only Download (1MB) |
|
Text
BAB 5.pdf Download (1MB) |
|
Text
DAFTAR PUSTAKA.pdf Download (1MB) |
|
Text
RIWAYAT HIDUP.pdf Restricted to Repository UPNVJ Only Download (1MB) |
|
Text
LAMPIRAN.pdf Restricted to Repository UPNVJ Only Download (2MB) |
|
Text
HASIL PLAGIARISME.pdf Restricted to Repository staff only Download (12MB) |
|
Text
ARTIKEL KI.pdf Restricted to Repository staff only Download (411kB) |
Abstract
Pasar Hasil Bumi is a marketplace platform focused on the sale of agricultural products by women farmer groups (Kelompok Wanita Tani) in the Tangerang area. As a newly developed platform, it has not yet implemented a recommendation system to enhance user experience and boost sales performance. This study aims to design and evaluate a recommendation system for the platform using a deep learning approach based on the two-tower model architecture. The model is designed to learn user and product representations separately in the form of embeddings, which are then used in the retrieval process to identify relevant product recommendations. Evaluation was carried out using Recall@K and Precision@K metrics at various values of K. The results show that the model achieved relatively high Recall@10 and Precision@1 scores, at 0.547099 and 0.195868 respectively. Precision values decrease as K increases, reflecting the trade-off between recommendation breadth and accuracy. Based on these results, the model is considered feasible for implementation on the Pasar Hasil Bumi platform, with the recommendation that performance should be monitored periodically to adapt to changes in user preferences.
| Item Type: | Thesis (Skripsi) |
|---|---|
| Additional Information: | [No.Panggil: 2110511054] [Pembimbing: Neny Rosmawarni] [Penguji 1: Musthofa Galih Pradana] [Penguji 2: Nurul Afifah Arifuddin] |
| Uncontrolled Keywords: | Recommendation System, Two-Tower Model, Deep Learning, Embedding, Marketplace |
| Subjects: | T Technology > T Technology (General) |
| Divisions: | Fakultas Ilmu Komputer > Program Studi Informatika (S1) |
| Depositing User: | M. NAUFALDI FADHLIRRAHMAN |
| Date Deposited: | 12 Jul 2025 22:08 |
| Last Modified: | 18 Jul 2025 03:43 |
| URI: | http://repository.upnvj.ac.id/id/eprint/37341 |
Actions (login required)
 |
View Item |