arXiv (Cornell University) · 2017 · 54 citations · 0 references
ComputingComputer ScienceForecastingMachine LearningTime Series AnalysisComputational Time Series AnalysisDeep LearningTime Series AnalyticsTime Series ForecastingTime Series ModelingTime Series PredictionAutoregressive ModelsAutoregressive Time Series ModelsBenchmark DatasetsConvolutional Neural NetworksMultivariate Time Series ForecastingMultivariate Time Series ModelingRecurrent Neural NetworksTime Series Representation Learning
We propose Significance-Offset Convolutional Neural Network, a deep\nconvolutional network architecture for regression of multivariate asynchronous\ntime series. The model is inspired by standard autoregressive (AR) models and\ngating mechanisms used in recurrent neural networks. It involves an AR-like\nweighting system, where the final predictor is obtained as a weighted sum of\nadjusted regressors, while the weights are datadependent functions learnt\nthrough a convolutional network. The architecture was designed for applications\non asynchronous time series and is evaluated on such datasets: a hedge fund\nproprietary dataset of over 2 million quotes for a credit derivative index, an\nartificially generated noisy autoregressive series and UCI household\nelectricity consumption dataset. The proposed architecture achieves promising\nresults as compared to convolutional and recurrent neural networks.\n