Japanese Interest Rate Forecast Considering the Linkage of Global Markets Using Machine Learning Methods

Yoshiyuki Suimon; Hiroki Sakaji; Kiyoshi Izumi; Takashi Shimada; Hiroyasu Matsushima

doi:10.52731/ijscai.v4.i1.500

Yoshiyuki Suimon University of Tokyo
Hiroki Sakaji University of Tokyo
Kiyoshi Izumi University of Tokyo
Takashi Shimada University of Tokyo
Hiroyasu Matsushima University of Tokyo

DOI: https://doi.org/10.52731/ijscai.v4.i1.500

Keywords: Interest Rate Forecast, Japanese Government Bond, Machine Learning, Neural Network, US Treasury Bond, Yield Curve

Abstract

In recent years, overseas financial system crises (e.g., Lehman shock and European debt crisis) and the effects of monetary policy changes by US and European central banks exerted major influence on the Japanese interest rates market. In this research, we developed a forecasting model of Japanese interest rate based on a variety of machine learning methods, by considering the information obtained from overseas rates markets and currency markets. Finally, we confirmed that the prediction accuracy of Japanese long-term interest rate improved by using the US interest rates data in addition to the Japanese interest rates data for machine learning. Furthermore, we confirmed that the prediction accuracy increased by using US and Japanese rates markets data in recent years, particularly after 2006. This result suggests that information of overseas interest rates can be used to forecast Japanese rates market nowadays.

References

Michael C. Münnix, Takashi Shimada, Rudi Schäfer, Francois Leyvraz, Thomas H. Seligman, Thomas Guhr and H Eugene Stanley, "Identifying states of a financial market," Scientific reports, Vol.2, No.644, 2012

Charles Nelson and Andrew F Siegel, “Parsimonious Modeling of Yield Curves,” The Journal of Business, Vol.60, No.4, pp.473-489, 1987

Yoshiyuki Suimon, “Fluctuation model of JGB yield curve using machine learning and the interest rate prediction,” The Japanese Society for Artificial Intelligence, SIG-FIN, No.21, pp.46-49, 2018

Sepp Hochreiter and Jürgen Schmidhuber, “Long Short-Term Memory, Neural Computation,” Vol.9, No.8, pp.1735-1780, 1997

Felix A. Gers, Jürgen Schmidhuber and Fred A. Cummins, “Learning to Forget: Continual Prediction with LSTM,” Neural Computation, Vol.12, No.10, pp.2451-2471, 2000

Francis X. Diebold and Canlin Li, “Forecasting the term structure of government bond yields,” Journal of Econometrics, Vol.130, pp.337-364, 2006

Haim Reisman and Gady Zohar, “Short-Term Predictability of the Term Structure,” The Journal of Fixed Income, Vol.14, No.3, pp7-14, 2004

Emanuel Moench, “Forecasting the yield curve in a data-rich environment: A no-arbitrage factor-augmented VAR approach,” Journal of Econometrics, Vol.146, No.1, pp26-43, 2008

Sydney C. Ludvigson and Serena Ng Author, “Macro Factors in Bond Risk Premia,” The Review of Financial Studies, Vol.22, No.12, pp.5027–5067, 2009

Sneha Soni, “Applications of ANNs in stock market prediction: a survey,” International Journal of Computer Science & Engineering Technology, Vol.2, No.3, pp.71-83, 2011

Dennis Olson and Charles Mossman, “Neural network forecasts of Canadian stock returns using accounting ratios,” International Journal of Forecasting, Vol.19, No.3, pp.453-465, 2003

Christopher Krauss, Xuan Anh Do and Nicolas Huck, “Deep neural networks, gradient-boosted trees, random forests: Statistical arbitrage on the S&P 500,” European Journal of Operational Research, Vol.259, No.2, pp.689-702, 2017

Dixon Matthew, Klabjan Diego and Bang Jin Hoon, “Classification-based financial markets prediction using deep neural networks,” Algorithmic Finance, Vol.6, No.3-4, pp.67-77, 2017