Paper Info
Title
Using Kalman-Filtered Radial Basis Function Networks to Forecast Changes in the ISEQ Index
Abstract
A Kalman-Filtered Feature-space approach is taken to forecast changes in the ISEQ (Irish Stock Exchange Equity Overall) Index using the previous five days' lagged returns solely as inputs. The resulting model is tantamount to a time-varying (adaptive) technical trading rule, one which achieves an out-of-sample Sharpe ('reward-to-variability') Ratio far superior to the 'buy-and-hold' strategy and its popular 'crossing moving-average' counterparts. The approach is contrasted to Recurrent Neural Network models and with other previous attempts to combine Kalman-Filtering concepts with (more traditional) Multi-layer Perceptron Network models. The new method proposed is found to be simple to implement, and, based on preliminary results presented here, might be expected to perform well for this type of problem.
Year
DOI
Venue
2007
10.1007/978-3-540-71805-5_25
Proceedings of the 2007 EvoWorkshops 2007 on EvoCoMnet, EvoFIN, EvoIASP,EvoINTERACTION, EvoMUSART, EvoSTOC and EvoTransLog: Applications of Evolutionary Computing
Keywords
Field
DocType
recurrent neural network model,multi-layer perceptron network model,kalman-filtered radial basis function,kalman-filtered feature-space approach,irish stock exchange equity,previous attempt,iseq index,forecast changes,kalman-filtering concept,preliminary result,new method,out-of-sample sharpe,resulting model,indexation,feature space,radial basis function network,stock exchange,variable ratio,moving average,kalman filter,recurrent neural network
Econometrics,Economics,Radial basis function network,Radial basis function,Recurrent neural network,Kalman filter,Sharpe ratio,Perceptron,Network model,Technical analysis
Conference
Volume
ISSN
Citations 
4448
0302-9743
0
PageRank 
References 
Authors
0.34
1
1
Name
Order
Citations
PageRank
David Edelman100.34