Department of Software Technology
Vienna University of Technology
Partially Recurrent Neural Networks in Stock Forecasting
Stock market data represent time-series data par excellence. The challenge for neural networks in such an environment is the representation of the temporal organization inherent in the input data. Conventionally, the temporal organization is approximated with a sliding windows technique when using standard feedforward neural networks such as the Multi-Layer Perceptron as the underlying model during the learning process. This approach suffers from a rather random selection of the sliding windows's actual size. We show that a more compact representation can be achieved by using partially recurrent neural networks. Moreover, the forecasting results as the ultimate goal of the application are improved significantly.
Up
Comments: rauber@ifs.tuwien.ac.at