2020/04/24 by Johannes Bleher, Bleher, Johannes, Michael Bleher +3
Decision Sciences · Economics, Econometrics and Finance · #62P05 #Applications (stat.AP) #Complex Systems and Time Series Analysis #Econometrics (econ.EM) #FOS: Computer and information sciences #FOS: Economics and business #Financial Markets and Investment Strategies #Mathematical Finance (q-fin.MF) #Statistical Finance (q-fin.ST) #Stock Market Forecasting Methods #Trading and Market Microstructure (q-fin.TR)
paper · pdf · doi:10.48550/arxiv.2004.11953
openalex publication_date 2020/04/24 · openalex created_date 2022/07/26 · openalex updated_date 2026/07/28
We propose a microscopic model to describe the dynamics of the fundamental\nevents in the limit order book (LOB): order arrivals and cancellations. It is\nbased on an operator algebra for individual orders and describes their effect\non the LOB. The model inputs are arrival and cancellation rate distributions\nthat emerge from individual behavior of traders, and we show how prices and\nliquidity arise from the LOB dynamics. In a simulation study we illustrate how\nthe model works and highlight its sensitivity with respect to assumptions\nregarding the collective behavior of market participants. Empirically, we test\nthe model on a LOB snapshot of XETRA, estimate several linearized model\nspecifications, and conduct in- and out-of-sample forecasts.The in-sample\nresults based on contemporaneous information suggest that our model describes\nreturns very well, resulting in an adjusted R2 of roughly 80%. In the more\nrealistic setting where only past information enters the model, we observe an\nadjusted R2 around 15%. The direction of the next return can be predicted\n(out-of-sample) with an accuracy above 75% for time horizons below 10 minutes.\nOn average, we obtain an RMSPE that is 10 times lower than values documented in\nthe literature.\n