토픽 모델링과 LSTM을 사용한 KOSPI 지수 예측
KOSPI index prediction using topic modeling and LSTM
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
본 연구는 토픽 모델링과 장단기 기억(LSTM) 신경망을 결합하여 한국 종합주가지수(KOSPI) 예측의정확도를 향상하는 방법을 제안한다. 본 논문에서는 LDA(Latent Dirichlet Allocation) 기법을 이용해금융 뉴스 데이터에서 금리 인상 및 인하와 관련된 10개의 주요 주제를 추출하고, 추출된 주제를 과거KOSPI 지수와 함께 LSTM 모델에 입력하여 KOSPI 지수를 예측하는 모델을 제안한다. 제안된 모델은과거 KOSPI 지수를 LSTM 모델에 입력하여 시계열 예측 방법과 뉴스 데이터를 입력하여 토픽 모델링하는 방법을 결합하여 KOSPI 지수를 예측하는 특성을 가진다. 제안된 모델의 성능을 검증하기 위해, 본 논문에서는 LSTM의 입력 데이터의 종류에 따라 4개의 모델(LSTM_K 모델, LSTM_KNS 모델, LDA_K 모델, LDA_KNS 모델)을 설계하고 각 모델의 예측 성능을 제시하였다. 예측 성능을 비교한결과, 금융 뉴스 주제 데이터와 과거 KOSPI 지수 데이터를 입력으로 하는 LSTM 모델(LDA_K 모델)이가장 낮은 RMSE(Root Mean Square Error)를 기록하여 가장 좋은 예측 성능을 보였다.
Abstract
In this paper, we proposes a method to improve the accuracy of predicting the Korea Composite Stock Price Index (KOSPI) by combining topic modeling and Long Short-Term Memory (LSTM) neural networks. In this paper, we use the Latent Dirichlet Allocation (LDA) technique to extract ten major topics related to interest rate increases and decreases from financial news data. The extracted topics, along with historical KOSPI index data, are input into an LSTM model to predict the KOSPI index. The proposed model has the characteristic of predicting the KOSPI index by combining the time series prediction method by inputting the historical KOSPI index into the LSTM model and the topic modeling method by inputting news data. To verify the performance of the proposed model, this paper designs four models (LSTM_K model, LSTM_KNS model, LDA_K model, LDA_KNS model) based on the types of input data for the LSTM and presents the predictive performance of each model. The comparison of prediction performance results shows that the LSTM model (LDA_K model), which uses financial news topic data and historical KOSPI index data as inputs, recorded the lowest RMSE (Root Mean Square Error), demonstrating the best predictive performance.
참고문헌 (9)
- Hyeon Su Seung, "Time series data through stock price prediction improving prediction accuracy", Proceedings of Symposium of the Korean Institute of communications and Information Sciences, pp.985~986 (2021)
- Lee Kanghoon, "A Study on the Prediction of KOSPI Index Direction using Investor Sentiment Indicators and Lasso Model", Proceedings of Symposium of the Korean Institute of communications and Information Sciences, pp.885~886 (2023)
- Kim SeongGon, "A study on KOSPI direction forecasting using the combination of time separation and sentiment analysis", pp.2023
- Jang SeoHee, "KOSPI Index Movement Prediction Combining BERT sentiment analysis and LSTM neural networks", pp.2023
- Doo-Won Kang, "A study on Deep Learning-based Stock Price Prediction using News Sentiment Analysis", Journal of the Korea Society of Computer and Information, 27(8), pp.31~39 (2022)
- Kwangyee Ko, "Development of economic fluctuation topic indices and topic indices regression model for KOSPI200 index", Journal of the Korean Data And Information Science Society, 31(4), pp.579~594 (2020)[DOI]
- Kim, Sun Woong, "Development of Options Trading System using KOSPI 200Volatility Index", Journal of Information Technology Services, 13(2), pp.151~161 (2014)[DOI]
- Sohee Shin, "Estimation of KOSPI200 Index option volatility using Artificial Intelligence", Journal of the Korea Institute of Information and Communication Engineering, 26(10), pp.1423~1431 (2022)
- Nak Young Lee, "KOSPI200 futures index prediction using denoising filter and LSTM", Journal of the Korean Data And Information Science Society, 30(3), pp.645~654 (2019)[DOI]