This paper introduces a stock-picking algorithm that can be used to perform an optimal asset allocation for a large number of investment opportunities. The allocation scheme is based upon the idea of causal risk. Instead of referring to the volatility of the assets time series, the stock-picking algorithm determines the risk exposure of the portfolio by concerning the non-forecastability of the assets. The underlying expected return forecasts are based on time-delay recurrent error correction neural networks, which utilize the last model error as an auxiliary input to evaluate their own misspecification. We demonstrate the profitability of our stock-picking approach by constructing portfolios from 68 different assets of the German stock market. It turns out that our approach is superior to a preset benchmark portfolio. Copyright © 2005 John Wiley & Sons, Ltd.
[1]
W. Sharpe.
A Simplified Model for Portfolio Analysis
,
1963
.
[2]
Ralph Neuneier,et al.
Active Portfolio-Management based on Error Correction Neural Networks
,
2001,
NIPS.
[3]
E. Elton.
Modern portfolio theory and investment analysis
,
1981
.
[4]
Ralph Neuneier,et al.
Modeling Dynamical Systems by Error Correction Neural Networks
,
2002
.
[5]
Barak A. Pearlmutter.
Gradient calculations for dynamic recurrent neural networks: a survey
,
1995,
IEEE Trans. Neural Networks.
[6]
Geoffrey E. Hinton,et al.
Learning internal representations by error propagation
,
1986
.
[7]
John F. Kolen,et al.
Neural Network Architectures for the Modeling of Dynamic Systems
,
2001
.