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 UCI household electricity consumption dataset. The proposed architecture achieves promising results as compared to convolutional and recurrent neural networks.
Mikolaj Binkowski (Imperial College London)
Gautier Marti (Ecole Polytechnique AXA IM Chorus)
Philippe Donnat (Hellebore Capital Limited)
Related Events (a corresponding poster, oral, or spotlight)
2018 Oral: Autoregressive Convolutional Neural Networks for Asynchronous Time Series »
Thu Jul 12th 03:20 -- 03:30 PM Room Victoria