Forecasting Quoted Depth With the Limit Order Book

Abstract

Liquidity plays a vital role in the financial markets, affecting a myriad of factors including stock prices, returns, and risk. In the stock market, liquidity is usually measured through the order book, which captures the orders placed by traders to buy and sell stocks at different price points. The introduction of electronic trading systems in recent years made the deeper layers of the order book more accessible to traders and thus of greater interest to researchers. This paper examines the efficacy of leveraging the deeper layers of the order book when forecasting quoted depth—a measure of liquidity—on a per-minute basis. Using Deep Feed Forward Neural Networks, we show that the deeper layers do provide additional information compared to the upper layers alone.

Mutual Information between Order Book Layers

“…Research on the deeper layers of the limit order book generally suggests that the deeper layers include some information. For instance, Libman et al [10] showed that compared to the uppermost bid-ask layers, using information from the deeper layers improves accuracy in predicting the log quoted depth, which is a measure of liquidity. Cao [11] concluded that data from the deeper layers promotes price discovery, while Baruch [12] claims that the NYSE's open limit order book benefits traders.…”