Abstract
Recently, day trading, that is, short-term trading that sells/buys financial instruments multiple times within a single trading day is rapidly spreading. But, there are few studies about forecasting short-term foreign exchange rates. Against this background, this work proposes a method of forecasting short-term foreign exchange rates based on k-nearest neighbor (k-NN). The proposed method restricts the search range of k-NN, and avoids forecasting the exchange rate if a certain condition is satisfied. We experimentally evaluate the proposed method by comparing it with an existing k-NN based method, linear regression, and multi-layer perceptron in three metrics: the mean squared forecast error (MSFE), the mean correct forecast direction (MCFD), and the mean forecast trading return (MFTR). The results show the proposed method outperforms the other methods in terms of both MCFD and MFTR, which implies reducing the forecast error does not necessarily contribute to making profits.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
- 2.
The second dataset contains the year-end and New Year holidays during which the market is closed. Therefore, we had to use a longer period in the second dataset than in the first one to gather the same size of training data for each test day.
References
Choudhry, T., McGroarty, F., Peng, K., Wang, S.: High-frequency exchange-rate prediction with an artificial neural network. Intell. Syst. Account. Financ. Manage. 19(3), 170–178 (2012)
Granger, C.W.: Outline of forecast theory using generalized cost functions. Span. Econ. Rev. 1(2), 161–173 (1999)
Kia, A.N., Haratizadeh, S., Zare, H.: Prediction of USD/JPY exchange rate time series directional status by KNN with dynamic time warping AS distance function. Bonfring Int. J. Data Min. 3(2), 12 (2013)
Lee, T.H.: Loss functions in time series forecasting. Int. Encycl. Soc. Sci. 9, 495–502 (2008)
Meese, R.A., Rogoff, K.: Empirical exchange rate models of the seventies: Do they fit out of sample? J. Int. Econ. 14(1–2), 3–24 (1983)
Qian, B., Rasheed, K.: Foreign exchange market prediction with multiple classifiers. J. Forecast. 29(3), 271–284 (2010)
Yao, J., Tan, C.L.: A case study on using neural networks to perform technical forecasting of forex. Neurocomputing 34(1), 79–98 (2000)
Zhou, B.: High-frequency data and volatility in foreign-exchange rates. J. Bus. Econ. Stat. 14(1), 45–52 (1996)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Switzerland AG
About this paper
Cite this paper
Umemoto, H., Toyota, T., Ohara, K. (2018). k-NN Based Forecast of Short-Term Foreign Exchange Rates. In: Yoshida, K., Lee, M. (eds) Knowledge Management and Acquisition for Intelligent Systems. PKAW 2018. Lecture Notes in Computer Science(), vol 11016. Springer, Cham. https://doi.org/10.1007/978-3-319-97289-3_11
Download citation
DOI: https://doi.org/10.1007/978-3-319-97289-3_11
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-97288-6
Online ISBN: 978-3-319-97289-3
eBook Packages: Computer ScienceComputer Science (R0)