Autoregressive Convolutional Neural Networks for Asynchronous Time Series

Mikolaj Binkowski, Gautier Marti, Philippe Donnat

Abstract: We propose Significance-Offset Convolutional Neural Network, a deep convolutional network architecture for regression of multivariate asynchronous time series. The model is inspired by standard autoregressive (AR) models and gating mechanisms used in recurrent neural networks. It involves an AR-like weighting system, where the final predictor is obtained as a weighted sum of adjusted regressors, while the weights are data-dependent functions learnt through a convolutional network. The architecture was designed for applications on asynchronous time series and is evaluated on such datasets: a hedge fund proprietary dataset of over 2 million quotes for a credit derivative index, an artificially generated noisy autoregressive series and household electricity consumption dataset. The pro-posed architecture achieves promising results as compared to convolutional and recurrent neural networks. The code for the numerical experiments and the architecture implementation will be shared online to make the research reproducible.

TL;DR: Convolutional architecture for learning data-dependent weights for autoregressive forecasting of time series.

Keywords: neural networks, convolutional neural networks, time series, asynchronous data, regression