LSTM forecasting foreign exchange rates using limit order book

Katsuki Ito, Hitoshi Iima, Yoshihiro Kitamura*

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

6 Citations (Scopus)


We use long and short term memory (LSTM) to predict intraday returns in foreign exchange markets. As predictors, we use events in the limit order book. Compared to other models, our model predicts the movement of a 1-min midquote return. When we consider the bid-ask spread, this prediction does not bring economic gains. This result indicates that these events can contribute to price discovery and the studied markets efficiently set the spread.

Original languageEnglish
Article number102517
JournalFinance Research Letters
Publication statusPublished - 2022 Jun


  • LSTM
  • foreign exchange rate
  • limit order

ASJC Scopus subject areas

  • Finance


Dive into the research topics of 'LSTM forecasting foreign exchange rates using limit order book'. Together they form a unique fingerprint.

Cite this