On Error Correction Neural Networks for Economic Forecasting
This addresses forecasting accuracy for economists and financial analysts, but it is incremental as it builds on existing RNN methods.
The paper tackled the problem of missing input variables in economic forecasting by proposing Error Correction Neural Networks (ECNNs), which feed back previous errors to compensate, and tested them on stock market predictions, showing they outperformed RNNs, LSTMs, and hybrid models with de-noising.
Recurrent neural networks (RNNs) are more suitable for learning non-linear dependencies in dynamical systems from observed time series data. In practice all the external variables driving such systems are not known a priori, especially in economical forecasting. A class of RNNs called Error Correction Neural Networks (ECNNs) was designed to compensate for missing input variables. It does this by feeding back in the current step the error made in the previous step. The ECNN is implemented in Python by the computation of the appropriate gradients and it is tested on stock market predictions. As expected it out performed the simple RNN and LSTM and other hybrid models which involve a de-noising pre-processing step. The intuition for the latter is that de-noising may lead to loss of information.