Importance of Event Binary Features in Stock Price Prediction
In Korea, because of the high interest in stock investment, many researchers have attempted to predict stock prices using deep learning. Studies to predict stock prices have been continuously conducted. However, the type of stock data that is suitable for deep learning has not been established, and...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-02-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/10/5/1597 |
| _version_ | 1811268687686008832 |
|---|---|
| author | Yoojeong Song Jongwoo Lee |
| author_facet | Yoojeong Song Jongwoo Lee |
| author_sort | Yoojeong Song |
| collection | DOAJ |
| description | In Korea, because of the high interest in stock investment, many researchers have attempted to predict stock prices using deep learning. Studies to predict stock prices have been continuously conducted. However, the type of stock data that is suitable for deep learning has not been established, and it has not been confirmed that the developed stock prediction model can actually result in a profit. To date, designing a good deep learning model depends on how well the user can extract the features that represent all the characteristics of the training data. Among the various available features for training and test data, we determined that the use of event binary features can make stock price prediction models perform better. An event binary feature refers to a 0 or 1 value describing whether an indicator is satisfied (1) or not (0) for any given day and stock. We proposed and compared a stock price prediction model with three different feature combinations to verify the importance of binary features. As a result, we derived a prediction model that defeated the market (KOSPI and KODAQ (KOSPI (Korea Composite Stock Price Index) and KOSDAQ (Korean Securities Dealers Automated Quotations) is Korean stock indices)). The results suggest that deep learning is suitable for stock price prediction. |
| first_indexed | 2024-04-12T21:27:22Z |
| format | Article |
| id | doaj.art-ed4835895c504c0bbfd7fe56e58d3a51 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-04-12T21:27:22Z |
| publishDate | 2020-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-ed4835895c504c0bbfd7fe56e58d3a512022-12-22T03:16:08ZengMDPI AGApplied Sciences2076-34172020-02-01105159710.3390/app10051597app10051597Importance of Event Binary Features in Stock Price PredictionYoojeong Song0Jongwoo Lee1Department of IT Engineering, Sookmyung Women’s University, Cheongpa-ro 47-gil 100, Yongsan-gu, Seoul 140-742, KoreaDepartment of IT Engineering, Sookmyung Women’s University, Cheongpa-ro 47-gil 100, Yongsan-gu, Seoul 140-742, KoreaIn Korea, because of the high interest in stock investment, many researchers have attempted to predict stock prices using deep learning. Studies to predict stock prices have been continuously conducted. However, the type of stock data that is suitable for deep learning has not been established, and it has not been confirmed that the developed stock prediction model can actually result in a profit. To date, designing a good deep learning model depends on how well the user can extract the features that represent all the characteristics of the training data. Among the various available features for training and test data, we determined that the use of event binary features can make stock price prediction models perform better. An event binary feature refers to a 0 or 1 value describing whether an indicator is satisfied (1) or not (0) for any given day and stock. We proposed and compared a stock price prediction model with three different feature combinations to verify the importance of binary features. As a result, we derived a prediction model that defeated the market (KOSPI and KODAQ (KOSPI (Korea Composite Stock Price Index) and KOSDAQ (Korean Securities Dealers Automated Quotations) is Korean stock indices)). The results suggest that deep learning is suitable for stock price prediction.https://www.mdpi.com/2076-3417/10/5/1597deep learningstock price predictionnovel input featuresevent binary featurestechnical analysis |
| spellingShingle | Yoojeong Song Jongwoo Lee Importance of Event Binary Features in Stock Price Prediction Applied Sciences deep learning stock price prediction novel input features event binary features technical analysis |
| title | Importance of Event Binary Features in Stock Price Prediction |
| title_full | Importance of Event Binary Features in Stock Price Prediction |
| title_fullStr | Importance of Event Binary Features in Stock Price Prediction |
| title_full_unstemmed | Importance of Event Binary Features in Stock Price Prediction |
| title_short | Importance of Event Binary Features in Stock Price Prediction |
| title_sort | importance of event binary features in stock price prediction |
| topic | deep learning stock price prediction novel input features event binary features technical analysis |
| url | https://www.mdpi.com/2076-3417/10/5/1597 |
| work_keys_str_mv | AT yoojeongsong importanceofeventbinaryfeaturesinstockpriceprediction AT jongwoolee importanceofeventbinaryfeaturesinstockpriceprediction |