Conditional Time Series Forecasting with Convolutional Neural Networks
This provides a time-efficient and easy-to-implement alternative for financial forecasting, though it is incremental as it adapts an existing deep learning method to a specific domain.
The authors tackled conditional time series forecasting by adapting the WaveNet architecture with dilated convolutions and parallel filters, showing that it outperforms autoregressive and LSTM models on financial datasets like S&P500 and exchange rates.
We present a method for conditional time series forecasting based on an adaptation of the recent deep convolutional WaveNet architecture. The proposed network contains stacks of dilated convolutions that allow it to access a broad range of history when forecasting, a ReLU activation function and conditioning is performed by applying multiple convolutional filters in parallel to separate time series which allows for the fast processing of data and the exploitation of the correlation structure between the multivariate time series. We test and analyze the performance of the convolutional network both unconditionally as well as conditionally for financial time series forecasting using the S&P500, the volatility index, the CBOE interest rate and several exchange rates and extensively compare it to the performance of the well-known autoregressive model and a long-short term memory network. We show that a convolutional network is well-suited for regression-type problems and is able to effectively learn dependencies in and between the series without the need for long historical time series, is a time-efficient and easy to implement alternative to recurrent-type networks and tends to outperform linear and recurrent models.