Journal of Industrial Convergence (산업융합연구)

DAEHAN Society of Industrial Management (대한산업경영학회)
권호 표지
DOI QR코드

DOI QR Code

Futures Price Prediction based on News Articles using LDA and LSTM

LDA와 LSTM를 응용한 뉴스 기사 기반 선물가격 예측

  • 주진현 (호서대학교 AI융합학부) ;
  • 박근덕 (호서대학교 컴퓨터공학부)
  • Received : 2022.12.10
  • Accepted : 2023.01.20
  • Published : 2023.01.28
Download PDF
⟨ Previous Next ⟩

Abstract

As research has been published to predict future data using regression analysis or artificial intelligence as a method of analyzing economic indicators. In this study, we designed a system that predicts prospective futures prices using artificial intelligence that utilizes topic probability data obtained from past news articles using topic modeling. Topic probability distribution data for each news article were obtained using the Latent Dirichlet Allocation (LDA) method that can extract the topic of a document from past news articles via unsupervised learning. Further, the topic probability distribution data were used as the input for a Long Short-Term Memory (LSTM) network, a derivative of Recurrent Neural Networks (RNN) in artificial intelligence, in order to predict prospective futures prices. The method proposed in this study was able to predict the trend of futures prices. Later, this method will also be able to predict the trend of prices for derivative products like options. However, because statistical errors occurred for certain data; further research is required to improve accuracy.

경제지표를 분석하는 방법으로 회귀 분석이나, 인공지능을 활용하여 미래의 데이터를 예측하는 연구가 발표되었다. 본 연구에서는 토픽모델링을 사용하여 과거 뉴스 기사로부터 얻은 주제 확률 데이터를 이용한 인공지능으로 미래 선물 가격을 예측하는 시스템을 구상하였다. 과거 뉴스 기사로부터 비지도학습을 통한 문서의 주제를 추출할 수 있는 LDA 방법으로 각 뉴스 기사 주제 확률 분포 데이터를 얻을 수 있고, 해당 데이터를 인공지능의 RNN의 파생 구조인 LSTM의 입력 데이터로 활용함으로써 미래 선물 가격을 예측하였다. 본 연구에서 제안한 방법에서는 선물 가격의 추세를 예측할 수 있었고, 이를 활용하여 추후 옵션 상품 등의 파생 상품에 대한 가격 추세도 예측할 수 있을 것으로 보인다. 다만, 일부 데이터에 대해 오차가 발생하는 것이 확인되어 정확도 향상을 위한 추가적인 연구가 필요하다.

Keywords

References

  1. Yang Cheol Won, Lu Bing. (2019). Do Futures Prices Lead Spot Prices?:Evidence from the Chinese Market. The Research Institute of Future Industry Dankook University, 43(1), 55-71.
  2. Ko, K., Oh, S., & Baek, J. (2020). 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), 579-594. DOI : 10.7465/jkdi.2020.31.4.579
  3. Kim, I., Lee, A., Kim, J., & Choi, J. (2022). Analysis of Owner's Detached House Housing Needs Sentences Using LDA Topic Modeling. Korean Journal of Computational Design and Engineering, 27(4), 435-445. DOI : 10.7315/cde.2022.435
  4. Han, D.-H., & Lee, Y.-K. (2021). Design of ActionBased Web Crawler Structural Configuration for Multi-Website Management. KIISE Transactions on Computing Practices, 27(2), 98-103. DOI : 10.5626/ktcp.2021.27.2.98
  5. Choi, S. C., & Park, H. W. (2020). A Study on the Trend of Topic Modeling in South Korea using KCI Journal Publications. The Korean Data Analysis Society, 22(2), 815-826. DOI : 10.37727/jkdas.2020.22.2.815
  6. David M. Blei, Andrew Y. Ng, and Michael I. Jordan. 2003. Latent dirichlet allocation. J. Mach. Learn. Res. 3, null (3/1/2003), 993-1022.
  7. Blei, D.M., & McAuliffe, J.D. (2007). Supervised Topic Models. NIPS. DOI : 10.48550/arXiv.1003.0783
  8. Roberts, M.E., Stewart, B.M., Tingley, D., Lucas, C., Leder-Luis, J., Gadarian, S.K., Albertson, B. and Rand, D.G. (2014), Structural Topic Models for Open-Ended Survey Responses. American Journal of Political Science, 58: 1064-1082. DOI : 10.1111/ajps.12103
  9. David M. Blei and John D. Lafferty. 2006. Dynamic topic models. In Proceedings of the 23rd international conference on Machine learning (ICML '06). Association for Computing Machinery, New York, NY, USA, 113-120. DOI : 10.1145/1143844.1143859
  10. C. H. Kang (2021). A study on the trend of COVID19 perception through dynamic topic modeling and semantic network analysis using tweeter text data, master dissertation, Sungkyunkwan University, Seoul
  11. Wang, X., & McCallum, A. (2006). Topics over time. Proceedings of the 12th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining - KDD '06. DOI : 10.1145/1150402.1150450
  12. S. W. Lee, C. K. Ahn. (2017). Introduction and Development trend of Artificial Neural Networks. The Korean Institute of Electrical Engineers, 66(8), 36-41.
  13. Kihwan Choi. (2018). Recent Applications in Convolutional Neural Networks. Communications of the Korean Institute of Information Scientists and Engineers, 36(2), 25-31.
  14. Kim, S.-J., & Choi, B.-J. (2022). LSTM Model based Prediction of Daily confirmed cases of COVID-19 in Korea using Google Mobility Data. Journal of Korean Institute of Intelligent Systems, 32(4), 292-298. DOI : 10.5391/jkiis.2022.32.4.292
  15. Kim, S. W. (2022). Long Short-Term Memorybased Prediction Performance of COVID-19 Fear Index on Asset Prices: Stocks vs Cryptocurrencies. Asia-Pacific Journal of Convergent Research Interchange, 8(8), 45?58. DOI : 10.47116/apjcri.2022.08.05