Abstract— Developing short-term stockmarket trading
systems is a complex process, as there is a great deal of random
noise present in the time series data of individual securities.
The primary difficulty in training neural networks to identify
return expectations is to find variables to help identify the
signal present in the data. In this paper, the authors follow the
previously published Vanstone and Finnie methodology. They
develop a successful neural network, and demonstrate its
effectiveness as the core element of a financially viable trading
system.
Index Terms—stockmarket trading, neural networks,
trading systems
|