Using Self-Organizing Maps to Adjust Intra-Day Seasonality

21 Pages Posted: 9 May 2005 Last revised: 3 May 2013

See all articles by Walid Ben Omrane

Walid Ben Omrane

Brock University - Department of Finance, Operations and Information Systems (FOIS)

Eric de Bodt

NHH

Date Written: May 6, 2005

Abstract

The existence of an intra-day seasonality component within financial market variables (volatility, volume, activity,. . .), has been highlighted in many previous works. To adjust raw data from their cyclical component, many studies start by implementing the intra-daily average observations model (IAOM) and/or some smoothing techniques (e.g. the kernel method) in order to remove the day of the week effect. When seasonality involves only a deterministic component, IAOM method succeed in estimating periodicity almost without estimation error. However, when seasonality contains both deterministic and stochastic components (e.g. closed days), we show that either the IAOM or the kernel method fail to capture it. We introduce the use of the self-organizing maps (SOM) as a solution. SOM are based on neural network learning and nonlinear projections. Their flexibility allows capturing seasonality even in the presence of stochastic cycles.

Keywords: foreign exchange market, self-organizing maps, seasonality, high frequency data

JEL Classification: F31, C22

Suggested Citation

Ben Omrane, Walid and de Bodt, Eric, Using Self-Organizing Maps to Adjust Intra-Day Seasonality (May 6, 2005). Available at SSRN: https://ssrn.com/abstract=720441 or http://dx.doi.org/10.2139/ssrn.720441

Walid Ben Omrane (Contact Author)

Brock University - Department of Finance, Operations and Information Systems (FOIS) ( email )

Ontario, L2S 3A1
Canada

Eric De Bodt

NHH ( email )

Helleveien 30
Bergen, NO-5045
Norway

Do you have negative results from your research you’d like to share?

Paper statistics

Downloads
193
Abstract Views
2,207
Rank
283,739
PlumX Metrics