LOBSTER: Limit Order Book Reconstruction System ∗

By Ruihong Huang, T. Polak. 2011

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Universal features of price formation in financial markets: perspectives from deep learning (2018, methodology): “LSTM units are specially designed to efficiently encode temporal † Historical order book data was reconstructed from NASDAQ Level III data using the LOBSTER data engine (Huang and Polak 2011). sequences of data.”
Limit order books (2010, background): “However, recent advances in computational and storage capabilities have made it feasible to record data detailing all order flows at all prices, and tools have been developed to assist researchers with reconstructing the full LOB in certain markets (Huang and Polak 2011).”
Deep learning for limit order books (2016, unknown): “Historical limit order book data was reconstructed from NASDAQ Level III market data using the LOBSTER data engine (Huang and Polak 2011).”
Estimating the Spot Covariation of Asset Prices—Statistical Theory and Empirical Evidence (2014, background): “The latter reconstructs the order book from a message stream, which is part of Nasdaq’s historical Total View-ITCH data and contains all limit order submissions, cancellations, and executions on each trading day (see Huang and Polak 2011) on the Nasdaq market.”