Salma Nabila Lovyanti, . (2026) IMPLEMENTASI METODE HYBRID FILTERING UNTUK APLIKASI REKOMENDASI COWORKING SPACE BERBASIS MOBILE. Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.
![[img]](http://repository.upnvj.ac.id/style/images/fileicons/text.png) |
Text
ABSTRAK.pdf Download (7MB) |
|
Text
AWAL.pdf Download (7MB) |
|
Text
BAB I.pdf Restricted to Repository UPNVJ Only Download (6MB) |
|
Text
BAB II.pdf Restricted to Repository UPNVJ Only Download (6MB) |
|
Text
BAB III.pdf Restricted to Repository UPNVJ Only Download (6MB) |
|
Text
BAB IV.pdf Restricted to Repository UPNVJ Only Download (6MB) |
|
Text
BAB V.pdf Download (6MB) |
|
Text
DAFTAR PUSTAKA.pdf Download (6MB) |
|
Text
RIWAYAT HIDUP.pdf Restricted to Repository staff only Download (96kB) |
|
Text
LAMPIRAN.pdf Restricted to Repository UPNVJ Only Download (7MB) |
|
Text
HASIL PLAGIARISME.pdf Restricted to Repository staff only Download (33MB) |
|
Text
ARTIKEL KI.pdf Restricted to Repository staff only Download (551kB) |
Abstract
The development of flexible study and work patterns has increased the need for public places that support productive activities, but information regarding budget levels, facilities, locations, and place ratings remains scattered across multiple platforms and is not presented personally. This study aims to develop Cowspace, a mobile-based recommendation application for alternative study or work places in South Jakarta by implementing hybrid filtering that combines content-based filtering and collaborative filtering using 35 place records and 875 rating records obtained from 25 respondents. The application was developed using Flutter as the frontend, FastAPI as the backend, and MySQL as the database, while the recommendation models were evaluated offline using user-based 5-fold cross-validation with a minimum rating of 4 as the relevance threshold. The evaluation results show that collaborative filtering achieved the highest performance, with a Precision@5 of 0.9360, Recall@5 of 0.7735, F1@5 of 0.8393, NDCG@5 of 0.9630, and MAP@5 of 0.9418, while hybrid filtering with CBF and CF weights of 0.2 and 0.8 ranked second and outperformed content-based filtering. Unit testing, integration testing, and black box testing showed that all test scenarios were successfully completed, while User Acceptance Testing obtained a score of 94.82% and was categorized as highly feasible, indicating that Cowspace successfully integrated the recommendation model into a mobile application and provided place recommendations based on user preferences and rating patterns.
| Item Type: | Thesis (Skripsi) |
|---|---|
| Additional Information: | [No.Panggil: 2210511069] [Pembimbing 1: Widya Cholil] [Pembimbing 2: Neny Rosmawarni] [Penguji 1: Musthofa Galih Pradana] [Penguji 2: Muhammad Panji Muslim] |
| Uncontrolled Keywords: | Recommendation System, Hybrid Filtering, Content-Based Filtering, Collaborative Filtering, Coworking Space, Mobile Application. |
| Subjects: | Q Science > QA Mathematics > QA75 Electronic computers. Computer science Q Science > QA Mathematics > QA76 Computer software |
| Divisions: | Fakultas Ilmu Komputer > Program Studi Informatika (S1) |
| Depositing User: | SALMA NABILA LOVYANTI |
| Date Deposited: | 28 Jul 2026 08:58 |
| Last Modified: | 08 Sep 2026 06:05 |
| URI: | http://repository.upnvj.ac.id/id/eprint/51977 |
Actions (login required)
 |
View Item |