뉴스 감성 앙상블 학습을 통한 주가 예측기의 성능 향상
An Accurate Stock Price Forecasting with Ensemble Learning Based on Sentiment of News
0
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
Various studies have been conducted from the past to the present because stock price forecasts provide stability in the national economy and huge profits to investors. Recently, there have been many studies that suggest stock price prediction models using various input data such as macroeconomic indicators and emotional analysis. However, since each study was conducted individually, it is difficult to objectively compare each method, and studies on their impact on stock price prediction are still insufficient. In this paper, the effect of input data currently mainly used on the stock price is evaluated through the predicted value of the deep learning model and the error rate of the actual stock price. In addition, unlike most papers in emotional analysis, emotional analysis using the news body was conducted, and a method of supplementing the results of each emotional analysis is proposed through three emotional analysis models. Through experiments predicting Microsoft's revised closing price, the results of emotional analysis were found to be the most important factor in stock price prediction. Especially, when all of input data is used, error rate of ensembled sentiment analysis model is reduced by 58% compared to the baseline.
Abstract
Various studies have been conducted from the past to the present because stock price forecasts provide stability in the national economy and huge profits to investors. Recently, there have been many studies that suggest stock price prediction models using various input data such as macroeconomic indicators and emotional analysis. However, since each study was conducted individually, it is difficult to objectively compare each method, and studies on their impact on stock price prediction are still insufficient. In this paper, the effect of input data currently mainly used on the stock price is evaluated through the predicted value of the deep learning model and the error rate of the actual stock price. In addition, unlike most papers in emotional analysis, emotional analysis using the news body was conducted, and a method of supplementing the results of each emotional analysis is proposed through three emotional analysis models. Through experiments predicting Microsoft's revised closing price, the results of emotional analysis were found to be the most important factor in stock price prediction. Especially, when all of input data is used, error rate of ensembled sentiment analysis model is reduced by 58% compared to the baseline.
참고문헌 (24)
- E. F. FAMA, "Efficient Capital Markets a Review of Theory and Empirical Work", The Fama Portfolio, pp.76~121 (2021)
- M. D. Godfrey, "The Random Walk Hypothesis of Stock Market Behavior", Kyklos, 17(1), pp.1~30 (1964)
- T. Gao, "Applying Long Short Term Momory Neural Networks for Predicting Stock Closing Price", 2017 8th IEEE International Conference on Software Engineering and Service Science (ICSESS), pp.575~578 (2017)
- J. G. De Gooijer, "25 years of IIF time Series Forecasting: a Selective Review", International Journal of Forecasting, 22(3), pp.443~473 (2006)
- S. Hochreiter, "Long Short-Term Memory", Neural Computation, 9(8), pp.1735~1780 (1997)
- K. Cho, "On the Properties of Neural Machine Translation:Encoder-decoder Approaches", arXiv preprint arXiv:1409.1259, ~ (2014)
- Y. S. Kim, "Analysis of the Relationship Between Stock Prices and Macroeconomic Variables", pp.99~12 (1999), Bank Of Korea
- P. S. Cho, "he Stock Forecasting Model using Bidirectional LSTM and Reinforcement Learning", PhD, pp.2021
- 신동하, "RNN과 LSTM을 이용한 주가 예측율 향상을 위한 딥러닝 모델", 한국정보기술학회논문지, 15(10), pp.9~16 (2017), 한국정보기술학회[DOI]
- 홍성혁, "거시지표와 딥러닝 알고리즘을 이용한 자동화된 주식 매매 연구", 디지털융복합연구, 18(11), pp.267~272 (2020), 한국디지털정책학회[DOI]
- W. Antweiler, "The Information Content of Internet Stock Message Board", J Finance, 59(3), pp.1259~1294 (2004)
- M. Baker, "Investor Sentiment and the Cross Section of Stock Returns", The Journal of Finance, 61(4), pp.1645~1680 (2006)
- 김명진, "SNS감성 분석을 이용한 주가 방향성 예측: 네이버 주식토론방 데이터를 이용하여", 한국전자거래학회지, 25(4), pp.61~75 (2020), 한국전자거래학회[DOI]
- J. G. Koh, "Stock Price Index Prediction Program Using Deep Learning Techniques", Proceedings of the Korean Society of Computer Information Conference, pp.525~526 (2021)
- 홍성혁, "A study on stock price prediction system based on text mining method using LSTM and stock market news", 디지털융복합연구, 18(7), pp.223~228 (2020), 한국디지털정책학회[DOI]
- E. Alickovic, "Normalized Neural Networks for Breast Cancer Classification", nternational Conference on Medical and Biological Engineering, pp.519~524 (2019), Springer
- C. Hutto, "Vader: A Parsimonious Rule-based Model for Sentiment Analysis of Social Media Text", Proceedings of the International AAAI Conference on Web and Social Media, 8(1), pp.216~225 (2015)
- J. Devlin, "Bert:Pre-training of Deep Bidirectional Transformers for Language Understanding", arXiv preprint arXiv:1810.04805, ~ (2018)
- D. Araci, "Finbert: Financial Sentiment Analysis with Pre-trained Language Models", arXiv preprint arXiv:1908.10063, ~ (2019)
- T. Mikolov, "Efficient Estimation of Word Representations in Vector Space", arXiv preprint arXiv:1301.3781, ~ (2013)
- 강인수, "영어 트위터 감성 분석을 위한 SentiWordNet 활용 기법 비교", 한국지능시스템학회 논문지, 23(4), pp.317~324 (2013), 한국지능시스템학회
- T. Mikolov, "Efficient Estimation of Word Representations in Vector Space", arXiv preprint arXiv:1301.3781, ~ (2013)
- T, Fischer, "Deep Learning with Long Short-term Memory Networks for Financial Market Predictions", European Journal of Operational Research, 270(2), pp.654~669 (2018)
- X. Shi, "Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting", Advances in Neural Information Processing Systems, pp.802~810 (2015)