Deep Limit Order Book Forecasting

arXiv:2403.09267v1 Announce Type: cross
Abstract: We exploit cutting-edge deep learning methodologies to explore the predictability of high-frequency Limit Order Book mid-price changes for a heterogeneous set of stocks traded on the NASDAQ exchange. In so doing, we release `LOBFrame', an open-source code base, to efficiently process large-scale Limit Order Book data and quantitatively assess state-of-the-art deep learning models' forecasting capabilities. Our results are twofold. We demonstrate that the stocks' microstructural characteristics influence the efficacy of deep learning methods and that …

abstract art arxiv book code code base cs.lg data deep learning edge exploit explore forecasting nasdaq price process q-fin.tr release scale set state stocks type