Exchange rate prediction through ANN based on Kernel Regression

Xian Hua; Defu Zhang; Stephen C. H. Leung

doi:10.1109/BIFE.2010.20

Exchange rate prediction through ANN based on Kernel Regression

Xian Hua, Defu Zhang, Stephen C. H. Leung

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

8 Citations (Scopus)

Abstract

This paper represents a fusion model of functional link artificial neural network (FLANN) based on Kernel Regression (KR) for modeling and prediction of exchange rate time series. To predict the exchange rate, we process the exchange rate datasets with KR to smooth the noise. And then the smoothed datasets are nonlinearly expanded using the sine and cosine expansions before inputting to the FLANN model. Using exchange rates between US to British Pound, Indian Rupees and Japanese Yen, we conducted several experiments on exchange rate prediction. We compare the performance to the FLANN model without KR and to the adaptive exponential smoothing method (AES), and it is observed that the FLANN-KR model outperforms the two other methods. © 2010 IEEE.

Original language	English
Title of host publication	Proceedings - 3rd International Conference on Business Intelligence and Financial Engineering, BIFE 2010
Pages	39-43
DOIs	https://doi.org/10.1109/BIFE.2010.20
Publication status	Published - 2010
Event	3rd International Conference on Business Intelligence and Financial Engineering, BIFE 2010 - Hong Kong, China Duration: 13 Aug 2010 → 15 Aug 2010

Conference

Conference	3rd International Conference on Business Intelligence and Financial Engineering, BIFE 2010
Country/Territory	China
City	Hong Kong
Period	13/08/10 → 15/08/10

Research Keywords

Adaptive exponential smoothing method
Artificial neural network
Exchange rate prediction
Financial prediction
Kernel regression

Access Output

10.1109/BIFE.2010.20

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

@inproceedings{f9e756989ca74de3b9d5acb944fcf826,

title = "Exchange rate prediction through ANN based on Kernel Regression",

abstract = "This paper represents a fusion model of functional link artificial neural network (FLANN) based on Kernel Regression (KR) for modeling and prediction of exchange rate time series. To predict the exchange rate, we process the exchange rate datasets with KR to smooth the noise. And then the smoothed datasets are nonlinearly expanded using the sine and cosine expansions before inputting to the FLANN model. Using exchange rates between US to British Pound, Indian Rupees and Japanese Yen, we conducted several experiments on exchange rate prediction. We compare the performance to the FLANN model without KR and to the adaptive exponential smoothing method (AES), and it is observed that the FLANN-KR model outperforms the two other methods. {\textcopyright} 2010 IEEE.",

keywords = "Adaptive exponential smoothing method, Artificial neural network, Exchange rate prediction, Financial prediction, Kernel regression",

author = "Xian Hua and Defu Zhang and Leung, {Stephen C. H.}",

year = "2010",

doi = "10.1109/BIFE.2010.20",

language = "English",

isbn = "9780769541167",

pages = "39--43",

booktitle = "Proceedings - 3rd International Conference on Business Intelligence and Financial Engineering, BIFE 2010",

note = "3rd International Conference on Business Intelligence and Financial Engineering, BIFE 2010 ; Conference date: 13-08-2010 Through 15-08-2010",

}

Hua, X, Zhang, D & Leung, SCH 2010, Exchange rate prediction through ANN based on Kernel Regression. in Proceedings - 3rd International Conference on Business Intelligence and Financial Engineering, BIFE 2010., 5621725, pp. 39-43, 3rd International Conference on Business Intelligence and Financial Engineering, BIFE 2010, Hong Kong, China, 13/08/10. https://doi.org/10.1109/BIFE.2010.20

Exchange rate prediction through ANN based on Kernel Regression. / Hua, Xian; Zhang, Defu; Leung, Stephen C. H.
Proceedings - 3rd International Conference on Business Intelligence and Financial Engineering, BIFE 2010. 2010. p. 39-43 5621725.

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

TY - GEN

T1 - Exchange rate prediction through ANN based on Kernel Regression

AU - Hua, Xian

AU - Zhang, Defu

AU - Leung, Stephen C. H.

PY - 2010

Y1 - 2010

N2 - This paper represents a fusion model of functional link artificial neural network (FLANN) based on Kernel Regression (KR) for modeling and prediction of exchange rate time series. To predict the exchange rate, we process the exchange rate datasets with KR to smooth the noise. And then the smoothed datasets are nonlinearly expanded using the sine and cosine expansions before inputting to the FLANN model. Using exchange rates between US to British Pound, Indian Rupees and Japanese Yen, we conducted several experiments on exchange rate prediction. We compare the performance to the FLANN model without KR and to the adaptive exponential smoothing method (AES), and it is observed that the FLANN-KR model outperforms the two other methods. © 2010 IEEE.

AB - This paper represents a fusion model of functional link artificial neural network (FLANN) based on Kernel Regression (KR) for modeling and prediction of exchange rate time series. To predict the exchange rate, we process the exchange rate datasets with KR to smooth the noise. And then the smoothed datasets are nonlinearly expanded using the sine and cosine expansions before inputting to the FLANN model. Using exchange rates between US to British Pound, Indian Rupees and Japanese Yen, we conducted several experiments on exchange rate prediction. We compare the performance to the FLANN model without KR and to the adaptive exponential smoothing method (AES), and it is observed that the FLANN-KR model outperforms the two other methods. © 2010 IEEE.

KW - Adaptive exponential smoothing method

KW - Artificial neural network

KW - Exchange rate prediction

KW - Financial prediction

KW - Kernel regression

UR - http://www.scopus.com/inward/record.url?scp=78650105173&partnerID=8YFLogxK

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-78650105173&origin=recordpage

U2 - 10.1109/BIFE.2010.20

DO - 10.1109/BIFE.2010.20

M3 - RGC 32 - Refereed conference paper (with host publication)

SN - 9780769541167

SP - 39

EP - 43

BT - Proceedings - 3rd International Conference on Business Intelligence and Financial Engineering, BIFE 2010

T2 - 3rd International Conference on Business Intelligence and Financial Engineering, BIFE 2010

Y2 - 13 August 2010 through 15 August 2010

ER -

Exchange rate prediction through ANN based on Kernel Regression

Abstract

Conference

Research Keywords

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this