Queue Imbalance as a One-Tick-Ahead Price Predictor in a Limit Order Book
Abstract
We investigate whether the bid/ask queue imbalance in a limit order book (LOB) provides significant predictive power for the direction of the next mid-price movement. For each of 10 liquid stocks on Nasdaq, we fit logistic regressions between the queue imbalance and the direction of the subsequent mid-price movement, and we find a strongly statistically significant relationship in each case. Compared to a simple null model, we find that our logistic regression fits provide a considerable improvement in both binary and probabilistic classification of mid-price movements for large-tick stocks and a moderate improvement in both binary and probabilistic classification of mid-price movements for small-tick stocks. We also perform local logistic regression fits on the same data, and find that this semi-parametric approach slightly outperforms our logistic regression fits, at the expense of being more computationally intensive to implement.
