Temporal Logistic Neural Bag-of-Features for Financial Time series Forecasting leveraging Limit Order Book Data

Time series forecasting is a crucial component of many important applications, ranging from fore-casting the stock markets to energy load prediction. The high-dimensionality, velocity and variety ofthe data collected in many of these applications pose significant and unique challenges that must becarefully addressed for each of them. In this work, a novel Temporal Logistic Neural Bag-of-Fea-tures approach, that can be used to tackle these challenges, is proposed. The proposed method canbe effectively combined with deep neural networks, leading to powerful deep learning models fortime series analysis. However, combining existing BoF formulations with deep feature extractors posesignificant challenges: the distribution of the input features is not stationary, tuning the hyper-param-eters of the model can be especially difficult and the normalizations involved in the BoF model cancause significant instabilities during the training process. The proposed method is capable of overcom-ing these limitations by a employing a novel adaptive scaling mechanism and replacing the classicalGaussian-based density estimation involved in the regular BoF model with a logistic kernel. The effec-tiveness of the proposed approach is demonstrated using extensive experiments on a large-scale limitorder book dataset that consists of more than 4 million limit orders.