Susilo, Bagas Dwi (2025) The potential use of ChatGPT in recommending stock investment decisions in the indonesian capital market / Bagas Dwi Susilo</p>. Diploma thesis, Universitas Negeri Malang.
Full text not available from this repository.Abstract
p This study examines the potential of ChatGPT in generating investment recommendations in the Indonesian capital market particularly on the LQ45 index. Using a quantitative experimental design the model analyzes financial news sentiment company fundamentals stock price dynamics and macroeconomic indicators for the period from October 21 2024 to January 31 2025. This information is combined to produce Buy Hold and Sell recommendations that will be tested on real market performance. The evaluation is conducted through market performance testing and bootstrapping to assess prediction accuracy and statistical strength. The results show that ChatGPT s Buy signal provided an average return of 13.37% far exceeding the LQ45 benchmark of -13.30% while the Sell signal successfully identified stocks with declines greater than the average. The bootstrapping test confirmed that these results were not random with a significantly higher accuracy ratio than a random portfolio. These findings challenge the validity of the semi-strong form efficient market hypothesis and provide theoretical and practical contributions for investors in emerging markets /p
| Item Type: | Thesis (Diploma) |
|---|---|
| Divisions: | Fakultas Ekonomi dan Bisnis (FEB) > Departemen Akuntansi (AKU) > S1 Akuntansi |
| Depositing User: | library UM |
| Date Deposited: | 18 Sep 2025 04:29 |
| Last Modified: | 09 Sep 2025 03:00 |
| URI: | http://repository.um.ac.id/id/eprint/424520 |
Actions (login required)
 |
View Item |