Conditional Time Series Forecasting with Convolutional Neural Networks

TL;DR

This paper introduces a convolutional neural network architecture based on WaveNet for conditional time series forecasting, demonstrating its effectiveness and efficiency in financial data prediction tasks.

Contribution

It adapts WaveNet for multivariate time series forecasting, enabling fast, effective, and non-recurrent modeling of dependencies in financial data.

Findings

Convolutional network outperforms linear and LSTM models in forecasting accuracy.

The model effectively captures dependencies without long historical data.

It is computationally efficient and easy to implement.

Abstract

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.