Muhammad Rizki, . (2025) RANCANG BANGUN APLIKASI EDUKASI SAHAM DENGAN CHATBOT BERBASIS NATURAL LANGUAGE PROCESSING DAN PREDIKSI SAHAM MENGGUNAKAN LONG SHORT-TERM MEMORY. Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.
![[img]](http://repository.upnvj.ac.id/style/images/fileicons/text.png) |
Text
ABSTRAK.pdf Download (243kB) |
|
Text
AWAL.pdf Download (701kB) |
|
Text
BAB I.pdf Restricted to Repository UPNVJ Only Download (302kB) |
|
Text
BAB II.pdf Restricted to Repository UPNVJ Only Download (629kB) |
|
Text
BAB III.pdf Restricted to Repository UPNVJ Only Download (937kB) |
|
Text
BAB IV.pdf Restricted to Repository UPNVJ Only Download (3MB) |
|
Text
BAB V.pdf Download (279kB) |
|
Text
DAFTAR PUSTAKA.pdf Download (291kB) |
|
Text
DAFTAR RIWAYAT HIDUP.pdf Restricted to Repository UPNVJ Only Download (133kB) |
|
Text
LAMPIRAN.pdf Restricted to Repository UPNVJ Only Download (415kB) |
|
Text
HASIL PLAGIARISME.pdf Restricted to Repository staff only Download (35MB) |
|
Text
ARTIKEL KI.pdf Restricted to Repository staff only Download (830kB) |
Abstract
This study aims to design and develop a stock education web application that integrates a Natural Language Processing (NLP)-based chatbot and a Long Short-Term Memory (LSTM)-based stock price prediction model. The application is intended to enhance financial literacy, particularly among young investors who are increasingly active in the capital market. The chatbot, built with the Rasa framework, can respond to educational questions and stock price prediction requests within natural conversational contexts. The prediction system uses a multi-layer LSTM architecture trained on historical stock data of blue chip banking stocks (BBCA, BBRI, BMRI, and BBNI) from January 1, 2019 to May 14, 2025. The model was evaluated using Mean Absolute Error (MAE) and Root Mean Square Error (RMSE). BBCA achieved the best performance with an MAE of 0.021 and RMSE of 0.026, while BBNI showed the highest error with an MAE of 0.028 and RMSE of 0.033. Meanwhile, the chatbot achieved perfect performance with 100% scores in accuracy, precision, recall, and F1-score. The integration of educational modules, NLP chatbot, and LSTM-based prediction in a single platform provides a comprehensive, predictive, and interactive learning experience. Testing results confirm that the application effectively delivers educational content while producing accurate and responsive stock price predictions.
| Item Type: | Thesis (Skripsi) |
|---|---|
| Additional Information: | [No.Panggil: 2110511042] [Pembimbing 1: Indra Permana Solihin] [Pembimbing 2: I Wayan Rangga Pinastawa] [Penguji 1: Widya Cholil] [Penguji 2: Muhammad Panji Muslim] |
| Uncontrolled Keywords: | Stock Education, Chatbot, Natural Language Processing, LSTM, Stock Prediction. |
| Subjects: | H Social Sciences > HG Finance L Education > LC Special aspects of education > LC5201 Education extension. Adult education. Continuing education Q Science > QA Mathematics > QA75 Electronic computers. Computer science Q Science > QA Mathematics > QA76 Computer software T Technology > T Technology (General) |
| Divisions: | Fakultas Ilmu Komputer > Program Studi Informatika (S1) |
| Depositing User: | MUHAMMAD RIZKI |
| Date Deposited: | 06 Aug 2025 01:42 |
| Last Modified: | 06 Aug 2025 01:42 |
| URI: | http://repository.upnvj.ac.id/id/eprint/37306 |
Actions (login required)
 |
View Item |