No abstract

Abstract-Forecasting financial time-series has long been among the most challenging problems in financial market analysis. In order to recognize the correct circumstances to enter or exit the markets investors usually employ statistical models (or even simple qualitative methods). However, the inherently noisy and stochastic nature of markets severely limits the forecasting accuracy of the used models. The introduction of electronic trading and the availability of large amounts of data allow for developing novel machine learning techniques that address some of the difficulties faced by the aforementioned methods. In this work we propose a deep learning methodology, based on recurrent neural networks, that can be used for predicting future price movements from large-scale high-frequency timeseries data on Limit Order Books. The proposed method is evaluated using a large-scale dataset of limit order book events.

No abstract

Abstract-Classification of time-series data is a challenging problem with many real-world applications, ranging from identifying medical conditions from electroencephalography (EEG) measurements to forecasting the stock market. The well known Bag-of-Features (BoF) model was recently adapted towards timeseries representation. In this work, a neural generalization of the BoF model, composed of an RBF layer and an accumulation layer, is proposed as a neural layer that receives the features extracted from a time-series and gradually builds its representation. The proposed method can be combined with any other layer or classifier, such as fully connected layers or feature transformation layers, to form deep neural networks for time-series classification. The resulting networks are end-to-end differentiable and they can be trained using regular back-propagation. It is demonstrated, using two time-series datasets, including a large-scale financial dataset, that the proposed approach can significantly increase the classification metrics over other baseline and state-of-the-art techniques.