Bryan Yapdhika, . (2025) PERANCANGAN CHATBOT INFORMASI LITERASI KEUANGAN BERBASIS WEB APP DENGAN PENDEKATAN LARGE LANGUAGE MODEL MENGGUNAKAN MODEL QWEN. Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.
![[img]](http://repository.upnvj.ac.id/style/images/fileicons/text.png) |
Text
ABSTRAK.pdf Download (258kB) |
|
Text
AWAL.pdf Download (982kB) |
|
Text
BAB 1.pdf Restricted to Repository UPNVJ Only Download (408kB) |
|
Text
BAB 2.pdf Restricted to Repository UPNVJ Only Download (992kB) |
|
Text
BAB 3.pdf Restricted to Repository UPNVJ Only Download (874kB) |
|
Text
BAB 4.pdf Restricted to Repository UPNVJ Only Download (1MB) |
|
Text
BAB 5.pdf Download (276kB) |
|
Text
DAFTAR PUSTAKA.pdf Download (274kB) |
|
Text
RIWAYAT HIDUP.pdf Restricted to Repository UPNVJ Only Download (147kB) |
|
Text
LAMPIRAN.pdf Restricted to Repository UPNVJ Only Download (1MB) |
|
Text
HASIL PLAGIARISME.pdf Restricted to Repository staff only Download (26MB) |
|
Text
ARTIKEL.pdf Restricted to Repository staff only Download (744kB) |
Abstract
Financial literacy is a crucial understanding and ability that enables individuals to manage their finances wisely and avoid undesirable financial problems. However, the level of financial literacy in Indonesia remains relatively low compared to other countries in Asia and Southeast Asia. According to a 2023 survey by OJK and OECD, the majority of Indonesians still lack understanding of basic financial management concepts such as investment, financial planning, and the use of formal financial services. This limited understanding leads to low public participation in productive economic activities. Therefore, this research aims to develop a web based informational chatbot application using Gradio, leveraging Large Language Model (LLM) technology as an interactive alternative medium for financial literacy information. The methodology involves the use of a Qwen-based model that has been pre-trained on Indonesian language datasets specifically, the Sailor2 model, which will then be fine-tuned using a reparameterization approach, namely the LoRA technique, without the need to retrain the entire model. The results of this study show that the model designed to answer financial literacy questions achieved a perplexity score of 3.06, indicating the FinID model is confident in providing accurate responses within the financial literacy domain. The chatbot’s performance and functionality were successfully validated through Black Box Testing with a perfect score, and user assessment via User Acceptance Testing (UAT) confirmed that the application is well-received as an alternative medium for financial literacy information.
| Item Type: | Thesis (Skripsi) |
|---|---|
| Additional Information: | [No.Panggil: 2110511070] [Pembimbing 1: Supriyanto] [Pembimbing 2: Kharisma Wiati Gusti] [Penguji 1: Musthofa Galih Pradana] [Penguji 2: I Wayan Rangga Pinastawa] |
| Uncontrolled Keywords: | Financial Literacy, Large Language Model, Chatbot, LoRA, Qwen, Gradio |
| Subjects: | Q Science > Q Science (General) Q Science > QA Mathematics Q Science > QA Mathematics > QA75 Electronic computers. Computer science T Technology > T Technology (General) |
| Divisions: | Fakultas Ilmu Komputer > Program Studi Informatika (S1) |
| Depositing User: | BRYAN YAPDHIKA |
| Date Deposited: | 31 Jul 2025 03:43 |
| Last Modified: | 07 Aug 2025 01:10 |
| URI: | http://repository.upnvj.ac.id/id/eprint/37237 |
Actions (login required)
 |
View Item |