This paper proposes a new method for predicting jump arrivals in stock markets with high-frequency limit order book data. We introduce a new model architecture, based on Convolutional Long Short-Term Memory with attention, to apply time series representation learning with memory and to focus the...

Investors in stock markets face a huge amount of financial information. For that reason, they must decide how to distribute their trading effort across different securities. We propose a new measure of investor trade allocation between securities, called the trading signature . This measure,...

We provide evidence that recent losses amplify order book illiquidity shocks caused by non-scheduled news. Moreover, the faster markets' reaction to scheduled and non-scheduled news arrivals is in terms of order book illiquidity, the more illiquid the order book becomes; that is, a fast reaction...