Marbun, Elizabeth Gokmauli (2021) Peramalan Harga Saham Boeing Menggunakan Neural Network Berdasarkan Data Historis Saham dan Analisis Sentimen. Undergraduate thesis, Institut Teknologi Sepuluh Nopember.
![[thumbnail of 06211740000064-Undergraduate_Thesis.pdf]](http://repository.its.ac.id/style/images/fileicons/text.png) |
Text
06211740000064-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only until 1 October 2023. Download (1MB) | Request a copy |
|
Text
06211740000064-Undergraduate_Thesis.pdf Restricted to Repository staff only Download (1MB) | Request a copy |
Abstract
Bursa saham merupakan area bisnis yang menjanjikan. Potensi untuk memperoleh keuntungan (return) yang tinggi dalam waktu yang cukup singkat menjadi salah satu daya tarik dari bisnis ini. Peramalan terhadap harga saham menjadi hal yang sangat menarik dan menantang bagi peneliti maupun akademisi, dimana meskipun pergerakan harga saham sangat acak dan kompleks, belakangan ditemukan bahwa harga saham dapat diramalkan dengan akurasi tertentu. Media sosial saat ini dapat dengan sempurna mewakili opini publik tentang peristiwa terkini. Stocktwits yang telah menarik perhatian peneliti dan akademisi untuk mempelajari sentimen publik tentang saham perusahaan. Dalam penelitian ini dilakukan peramalan harga saham Boeing berdasarkan harga historis saham yang dibandingkan dengan peramalan harga saham berdasarkan gabungan data harga historis saham dan skor sentimen. Analisis sentimen menggunakan kamus leksikal Vader untuk memperoleh skor sentimen dari opini publik mengenai saham Boeing tahun 2019. Pada penelitian ini diperoleh hasil bahwa peramalan harga saham degan menggunakan gabungan data harga saham hisoris dan skor sentimen dapat menurunkan MAPE sebesar 15,12% dibandingkan peramalan yang hanya menggunakan data historis saham.
======================================================================================================
The stock market is a promising business area. The potential to earn high profits (return) in a fairly short time is one of the attractions of this business. Forecasting stock prices has become a very interesting and challenging thing for researchers and academics alike, where although stock price movements are very random and complex, it was recently discovered that stock prices can be predicted with a certain accuracy. Today's social media can perfectly represent public opinion about current events. Stocktwits that have attracted a lot of attention of researchers and academics to study public sentiment about a company's stock. In this study, Boeing stock price forecasting is based on historical stock prices compared to stock price forecasting based on a combination of stock historical price data and sentiment scores. Sentiment analysis uses Vader’s leksikal dictionary to obtain a sentiment score from public opinion about Boeing Stock’s in 2019. In this study, it was found that stock price forecasting using a combination of historical stock price data and sentiment scores can reduce MAPE by 15.12% compared to forecasting only using historical stock data.
| Item Type: | Thesis (Undergraduate) |
|---|---|
| Uncontrolled Keywords: | Stock Market, Long Short Term Memory, MAPE, Sentiment, StockTwits, Bursa Saham, Long Short Term Memory, MAPE, Sentimen, StockTwits |
| Subjects: | T Technology > T Technology (General) > T174 Technological forecasting |
| Divisions: | Faculty of Science and Data Analytics (SCIENTICS) > Statistics > 49201-(S1) Undergraduate Thesis |
| Depositing User: | Elizabeth Gokmauli Marbun |
| Date Deposited: | 03 Sep 2021 02:22 |
| Last Modified: | 03 Sep 2021 02:22 |
| URI: | http://repository.its.ac.id/id/eprint/91499 |
Actions (login required)
 |
View Item |