Convolutional neural networks can do time series forecasting. They can learn local patterns in time, and they can be modified to learn only from the history (ignoring the future) and to use a long look-back window when doing so. A further simple modification enables them to forecast not the mean, but arbitrary quantiles of the distribution. And one last thing to make this all work: the CNN forecaster's complexity and flexibility requires much data, that is, preferably multiple time series. When this is met, the proposed QCNN framework can be competitive. It is demonstrated on a financial problem of huge practical importance: Value at Risk forecasting. By contributing to the stability of financial systems, deep learning may find one further way to improve our lives.
↧