Work detail

Modelling Durations Using Artificial Neural Networks

Author: Mgr. Martin Žofka
Year: 2014 - winter
Leaders: doc. PhDr. Jozef Baruník Ph.D.
Work type: Economic Theory
Language: English
Pages: 68
Awards and prizes: M.A. with distinction from the Dean of the Faculty of Social Sciences for an excellent state-final examination performance.
Abstract: The thesis introduces Artificial Neural Networks (ANN) to the field of financial durations.
We begin by
reviewing the findings about financial durations and models applied to analyze them. ANNs are then
surveyed and one of the possible network architec
tures is selected for the forecasting. The selected
ANN is a feed
forward network, with one hidden layer, a sigmoid activation function and a genetic
algorithm for optimization. We use original and diurnally adjusted data for estimation and in contrast
other duration models, ANNs do not require data pre
processing. Therefore forecasts are
estimated in one step without remov
ing seasonalities for raw data.
The estimates of the ANN are
compared to estimates of the Autoregressive Conditional Duration (ACD) m
odel, which serves as a
benchmark for forecasting capabilities of the ANNs. The findings confirm that ANNs can be used to
model durations with a similar accuracy as the ACD model. In the case of raw data the model slightly
outperforms the ACD model, while
the opposite is true for adjusted data, however the forecasting
ability difference is not significan


McKinsey & Company