The prediction of stock market by natural language processing and deep learning

DOI IR Web Site Open Access

Bibliographic Information

Other Title
  • 自然言語処理と深層学習を用いた株式市場の予測
  • シゼン ゲンゴ ショリ ト シンソウ ガクシュウ オ モチイタ カブシキ シジョウ ノ ヨソク

Search this article

Description

Recently, there are many motivations to quantify text data and use them for investment because the technology of the natural language processing has progressed. In addition, the method by deep learning is received a lot of attention with the development of the information technology. Nowadays, it is shown that using deep learning for several data is effective, especially pictures or text. For this reason, a lot of researches or institutional investors start to use deep learning for prediction or analyze in financial market. In this study, we used the Monthly Report of Recent Economic and Financial Development and tried to estimate trends of market. Specifically, we attempted to predict trends of market with PCR (principal component regression) model and machine-learning models about deep learning based on the numbers of occurrence of the words in the report. Then, the goal of our research is to verify the effectiveness of the machine-learning models through comparison with PCR model. In the case, we applied a simple Recurrent Neural Network (RNN).

Journal

Keywords

Details 詳細情報について

Report a problem

Back to top