• Search Research Projects
  • Search Researchers
  • How to Use
  1. Back to previous page

Leveraging deep learning in the practical evaluation of finance theory

Research Project

Project/Area Number 19H01508
Research Category

Grant-in-Aid for Scientific Research (B)

Allocation TypeSingle-year Grants
Section一般
Review Section Basic Section 07060:Money and finance-related
Research InstitutionWaseda University

Principal Investigator

Kitamura Yoshihiro  早稲田大学, 社会科学総合学術院, 教授 (90409566)

Co-Investigator(Kenkyū-buntansha) 飯間 等  京都工芸繊維大学, 情報工学・人間科学系, 准教授 (70273547)
Project Period (FY) 2019-04-01 – 2023-03-31
Project Status Completed (Fiscal Year 2022)
Budget Amount *help
¥15,990,000 (Direct Cost: ¥12,300,000、Indirect Cost: ¥3,690,000)
Fiscal Year 2022: ¥2,470,000 (Direct Cost: ¥1,900,000、Indirect Cost: ¥570,000)
Fiscal Year 2021: ¥2,470,000 (Direct Cost: ¥1,900,000、Indirect Cost: ¥570,000)
Fiscal Year 2020: ¥2,730,000 (Direct Cost: ¥2,100,000、Indirect Cost: ¥630,000)
Fiscal Year 2019: ¥8,320,000 (Direct Cost: ¥6,400,000、Indirect Cost: ¥1,920,000)
Keywords深層学習 / 為替レート予測 / 指値注文 / LSTM / Long Short-Term Memory / 注文板情報 / 機械学習 / 指値注文板 / 為替レート / 金融資産価格変動予測
Outline of Research at the Start

▼研究課題の学術的重要性:人工知能を活用することで、ファイナンス理論の臨床的有効性を示す。ファイナンス理論の臨床的価値を証明し、机上の理論でないことを示す。
▼研究目的・研究方法:人工知能分野の一つである深層学習で、為替レート・ボラティリティを予測する。深層学習への入力変数として、ファイナンス理論がボラティリティとの関連を明らかにした「情報トレーダー」、「市場流動性」、「市場効率性」指標を採用。その入力をもとに深層学習はボラティリティ予測を行う。
▼研究課題の波及効果:本研究を通じて、人工知能を活用したファイナンス理論の臨床的有効性に対する評価方法を確立し、情報ファイナンスの新分野を創造・発信。

Outline of Final Research Achievements

The present study uses high-frequency time series data on exchange rates. We selected a deep learning model for time series analysis and conducted the analysis. Specifically, we used Long Short-Term Memory (LSTM) to test whether limit order book information in the exchange rate market is effective in predicting exchange rates. The deep learning model's predictive power exceeded that of the existing models, and the limit order information was found to be useful in predicting exchange rates.

Academic Significance and Societal Importance of the Research Achievements

本研究の目的は、人工知能の一つである「深層学習」でファイナンス理論を学習し、その学習が将来の為替レートの予測に貢献するかを研究することである。今回の研究は主に外国為替市場を研究対象としたが、この研究を通じて、人工知能(深層学習)を活用しファイナンス理論の臨床性を評価する流れを確立させることを目的とした。そのことで、情報工学分野で研究が進む深層学習をファイナンス理論の臨床性評価に活用する一連の流れを確立させた新分野の創造・発信を究極的目的とした。

Report

(5 results)
  • 2022 Annual Research Report   Final Research Report ( PDF )
  • 2021 Annual Research Report
  • 2020 Annual Research Report
  • 2019 Annual Research Report
  • Research Products

    (12 results)

All 2022 2021 2020

All Journal Article (9 results) (of which Int'l Joint Research: 1 results,  Peer Reviewed: 7 results,  Open Access: 3 results) Presentation (3 results) (of which Int'l Joint Research: 1 results)

  • [Journal Article] Generative Adversarial Network for Generating Different Types of Data2022

    • Author(s)
      Murota Shingo、Iima Hitoshi
    • Journal Title

      IEEJ Transactions on Electronics, Information and Systems

      Volume: 142 Issue: 7 Pages: 781-787

    • DOI

      10.1541/ieejeiss.142.781

    • ISSN
      0385-4221, 1348-8155
    • Year and Date
      2022-07-01
    • Related Report
      2022 Annual Research Report
    • Peer Reviewed
  • [Journal Article] Centralized and Accelerated Multiagent Reinforcement Learning Method with Automatic Reward Setting2022

    • Author(s)
      Sasaki Kaoru、Iima Hitoshi
    • Journal Title

      Transactions of the Institute of Systems, Control and Information Engineers

      Volume: 35 Issue: 3 Pages: 39-47

    • DOI

      10.5687/iscie.35.39

    • ISSN
      1342-5668, 2185-811X
    • Year and Date
      2022-03-15
    • Related Report
      2022 Annual Research Report
    • Peer Reviewed
  • [Journal Article] Estimating Systematic and Partial Exchange Rate Exposures: The Case of Japanese Firms2022

    • Author(s)
      Kim Jae H.、Kitamura Yoshihiro
    • Journal Title

      International Journal of Empirical Economics

      Volume: 01 Issue: 01 Pages: 1-31

    • DOI

      10.1142/s2810943022500044

    • Related Report
      2022 Annual Research Report 2021 Annual Research Report
    • Peer Reviewed / Open Access / Int'l Joint Research
  • [Journal Article] LSTM forecasting foreign exchange rates using limit order book2022

    • Author(s)
      Ito Katsuki、Iima Hitoshi、Kitamura Yoshihiro
    • Journal Title

      Finance Research Letters

      Volume: 47 Pages: 102517-102517

    • DOI

      10.1016/j.frl.2021.102517

    • Related Report
      2022 Annual Research Report 2021 Annual Research Report
    • Peer Reviewed
  • [Journal Article] Hyperheuristic Method Based on Deep Reinforcement Learning2022

    • Author(s)
      Iima Hitoshi、Nakamura Yoshiyuki
    • Journal Title

      2022 12th International Congress on Advanced Applied Informatics (IIAI-AAI)

      Volume: 0 Pages: 303-306

    • DOI

      10.1109/iiaiaai55812.2022.00068

    • Related Report
      2022 Annual Research Report
    • Peer Reviewed
  • [Journal Article] Genetic Algorithm with Machine Learning to Estimate the Optimal Objective Function Values of Subproblems2022

    • Author(s)
      Iima Hitoshi、Hazama Yohei
    • Journal Title

      ISMSI 2022: 2022 6th International Conference on Intelligent Systems, Metaheuristics & Swarm Intelligence

      Volume: 0 Pages: 1-8

    • DOI

      10.1145/3533050.3533051

    • Related Report
      2022 Annual Research Report
    • Peer Reviewed
  • [Journal Article] A lesson from the four recent large public Japanese FX interventions2020

    • Author(s)
      Kitamura Yoshihiro
    • Journal Title

      Journal of the Japanese and International Economies

      Volume: 57 Pages: 101087-101087

    • DOI

      10.1016/j.jjie.2020.101087

    • NAID

      210000186541

    • Related Report
      2020 Annual Research Report 2019 Annual Research Report
    • Peer Reviewed
  • [Journal Article] リカレントニューラルネットワークによる為替レートの予測2020

    • Author(s)
      伊藤 克輝 飯間 等 北村 能寛
    • Journal Title

      第82回全国大会講演論文集

      Volume: 1 Pages: 287-288

    • NAID

      170000182331

    • Related Report
      2020 Annual Research Report 2019 Annual Research Report
    • Open Access
  • [Journal Article] Price Discovery via Limit Order in FX Market2020

    • Author(s)
      Kitamura Yoshihiro
    • Journal Title

      SSRN Electronic Journal

      Volume: NA Pages: 140-140

    • DOI

      10.2139/ssrn.3740392

    • Related Report
      2020 Annual Research Report
    • Open Access
  • [Presentation] Price discovery of limit orders in the FX market2022

    • Author(s)
      Yoshihiro Kitamura
    • Organizer
      Vietnam Symposium in Banking and Finance
    • Related Report
      2022 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Price discovery of limit order in FX market2021

    • Author(s)
      北村能寛
    • Organizer
      日本ファイナンス学会秋季研究大会
    • Related Report
      2021 Annual Research Report
  • [Presentation] リカレントニューラルネットワークによる為替レートの予測2020

    • Author(s)
      伊藤 克輝 飯間 等 北村 能寛
    • Organizer
      情報処理学会
    • Related Report
      2020 Annual Research Report 2019 Annual Research Report

URL: 

Published: 2019-04-18   Modified: 2024-01-30  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi