BERT를 활용한 뉴스 감성분석과 거시경제지표 조합을 이용한 주가지수 예측
Stock prediction using combination of BERT sentiment Analysis and Macro economy index
1
조회
0
다운로드
24
인용
0
참고문헌
키워드
초록
주가지수는 한 국가의 경제 지표뿐만 아니라 투자판단의 지표로도 활용되므로 이를 예측하는 연구가지속해서 진행되고 있다. 주가지수 예측을 하는 작업은 기술적, 경제적 및 심리적 요인 등이 반영된것으로 예측의 정확도를 위해서는 복합적 요인을 고려해야 한다. 따라서 지수의 변동에 영향을 미치는요인들을 선별하여 반영한 주가지수 예측모델연구가 필요하다. 이와 관련한 기존 연구에서는 시장의변동을 만들어 내는 뉴스 정보 또는 거시 경제 지표를 각각 이용하거나, 몇 가지의 지표 조합만을반영한 예측 연구가 대부분이었다. 따라서 본 연구에서는 미국 다우존스지수 예측을 위해 뉴스 정보의감성 분석과 다양한 거시경제지표를 고려하여 효과적인 지표 조합을 제시하고자 한다. 뉴스 정보의감성 분석은 최신 자연어처리 기법인 BERT와 NLTK VADER를 사용하고, 예측모델은 주가예측모델로적합하다고 알려진 딥러닝 예측모델 LSTM을 적용하여 가장 효과적인 지표 조합을 제시했다.
Abstract
The stock index is used not only as an economic indicator for a country, but also as an indicator for investment judgment, which is why research into predicting the stock index is ongoing. The task of predicting the stock price index involves technical, basic, and psychological factors, and it is also necessary to consider complex factors for prediction accuracy. Therefore, it is necessary to study the model for predicting the stock price index by selecting and reflecting technical and auxiliary factors that affect the fluctuation of the stock price according to the stock price. Most of the existing studies related to this are forecasting studies that use news information or macroeconomic indicators that create market fluctuations, or reflect only a few combinations of indicators. In this paper, this we propose to present an effective combination of the news information sentiment analysis and various macroeconomic indicators in order to predict the US Dow Jones Index. After Crawling more than 93,000 business news from the New York Times for two years, the sentiment results analyzed using the latest natural language processing techniques BERT and NLTK, along with five macroeconomic indicators, gold prices, oil prices, and five foreign exchange rates affecting the US economy Combination was applied to the prediction algorithm LSTM, which is known to be the most suitable for combining numeric and text information. As a result of experimenting with various combinations, the combination of DJI, NLTK, BERT, OIL, GOLD, and EURUSD in the DJI index prediction yielded the smallest MSE value.
참고문헌 (31)
- Antonina Kloptchenko, "Combining data and text mining techniques for analysing financial reports", Intelligent Systems in Accounting, Finance & Management, 12(1), pp.29~41 (2004), Wiley[DOI]
- Ratto, Andrea Picasso, "Technical analysis and sentiment embeddings for market trend prediction", Expert Syst. Appl, 135, pp.60~70 (2019)
- S. K Kim, "The Study of the Financial Index Prediction Using the Equalized Multi-layer Arithmetic Neural Network", Journal of The Korea Society of Computer and Information, 8(33), pp.113~123 (2013)
- 어균선, "데이터마이닝 방법을 이용한 주가방향예측에 관한 연구: 단일분류기와 앙상블 분류기간 비교를 중심으로", 한국컴퓨터정보학회논문지, 22(11), pp.111~116 (2017), 한국컴퓨터정보학회[DOI]
- S. Deng, "Combining Technical Analysis with Sentiment Analysis for Stock Price Prediction", 2011 IEEE Ninth International Conference on Dependable, Autonomic and Secure Computing, pp.800~807 (2011)
- Zhai. Y., "Combining news and technical indicators in daily stock price trends prediction", Advances in Neural Networks Lecture Notes in Computer Science, 4, pp.1087~1096 (2007)
- Sirucek. Martin, "Macroeconomic variables and stock market: US review", International Journal of Computer Science and Management Studies, 12(3) (2012)
- In-Kyu. Kim, "Study for Exchange rate, Interest, Stock price Using Quasi-Likelihood Estimatorfor", Journal of The Korea Society of Computer and Information, 20(1), pp.255~256 (2012)
- Ulrich Oberndorfer, "Energy prices, volatility, and the stock market: Evidence from the Eurozone", Energy Policy, 37(12), pp.5787~5795 (2009), Elsevier BV[DOI]
- Farooq Malik, "Volatility transmission between oil prices and equity sector returns", International Review of Financial Analysis, 18(3), pp.95~100 (2009), Elsevier BV[DOI]
- Jer-Shiou Chiou, "Jump dynamics and volatility: Oil and the stock markets", Energy, 34(6), pp.788~796 (2009), Elsevier BV[DOI]
- Timotheos Angelidis, "US stock market regimes and oil price shocks", Global Finance Journal, 28, pp.132~146 (2015), Elsevier BV[DOI]
- The price of Gold and Stock Price Indices for the United States, "Smith G", the World Gold Council, 1~35 (2001)
- Jeremy C. Goh, "Can US economic variables predict the Chinese stock market?", Pacific-Basin Finance Journal, 22, pp.69~87 (2013), Elsevier BV[DOI]
- Athanasios Koulakiotis, "Exploring the interaction between stock price index and exchange rates: an asymmetric threshold approach", Applied Economics, 47(13), pp.1273~1285 (2015), Informa UK Limited[DOI]
- Nguyen Quang My, "The Impact of Economic Factors on the Foreign Exchange Rates between USA and Four Big Emerging Countries: China, India, Brazil and Mexico", International Finance and Banking, 3(1), pp.11~43 (2016), Macrothink Institute, Inc.[DOI]
- Athanasios Tsagkanos, "A long-run relationship between stock price index and exchange rate: A structural nonparametric cointegrating regression approach", Journal of International Financial Markets, Institutions and Money, 25, pp.106~118 (2013), Elsevier BV[DOI]
- Robert P. Schumaker, "Textual analysis of stock market prediction using breaking financial news", ACM Transactions on Information Systems, 27(2), pp.1~19 (2009), Association for Computing Machinery (ACM)[DOI]
- Gilbert, Eric, "Widespread Worry and the Stock Market", International AAAI Conference on Weblogs and Social Media (2010)
- Johan Bollen, "Twitter mood predicts the stock market", Journal of Computational Science, 2(1), pp.1~8 (2011), Elsevier BV[DOI]
- Lavrenko, Victor, "Mining of Concurrent Text and Time Series", KDD-2000 Workshop on Text Mining, 6, pp.37~44 (2000)
- Hutto, Clayton J., "VADER: A Parsimonious Rule-Based Model for Sentiment Analysis of Social Media Text", International AAAI Conference on Weblogs and Social Media, 8, pp.216~225 (2015)
- Devlin, Jacob, "BERT : Pre-training of Deep Bidirectional Transformers for Language Understanding", ArXiv : abs, 2019 (1810)
- 성노윤, "온라인 뉴스 및 거시경제 변수를 활용한 주가예측", Entrue Journal of Information Technology, 16(2), pp.41~54 (2017), 엘지씨엔에스
- Ehsan Hoseinzade, "CNNpred: CNN-based stock market prediction using a diverse set of variables", Expert Systems with Applications, 129, pp.273~285 (2019), Elsevier BV[DOI]
- Akita, Ryo, "Deep learning for stock prediction using numerical and textual information", 2016 IEEE, 2016, 1~6
- Kalchbrenner, Nal, "A Convolutional Neural Network for Modeling Sentences", ArXiv:1404.2188, ~ (2014)
- Siami-Namini, Sima, "Forecasting Economics and Financial Time Series: ARIMA vs. LSTM", ArXiv: abs, 2018 (1803)
- Mcnally, Sean, "Predicting the Price of Bitcoin Using Machine Learning", Euromicro International Conference on Parallel, Distributed and Network-based Processing, 26, pp.339~343 (2018)
- Lipton, Zachary Chase, "A Critical Review of Recurrent Neural Networks for Sequence Learning", ArXiv: abs, 2015
- "Christopher. Olah"[URL]