An Autoencoder (AE) is an independent feature extractor from data samples and a deep network can be obtained by stacking several AEs. This paper presents a novel hybrid stacked Autoencoder-based Deep Kernel-based Random Vector Functional Link Network (DKRVFLN-AE) for forecasting and trend...

We develop a microstructure model whose order ow is driven by a Cox-BESQ process. We derive important analytical properties of the Cox-BESQ process in order to explicit the stock price dynamics at different time scales, provide different parameter estimators and solve the optimal execution...