Stock price prediction is a challenging task, but machine learning methods have recently been used successfully for this purpose. In this paper, we extract over 270 hand-crafted features (factors) inspired by technical and quantitative analysis and tested their validity on short-term mid-price...

The bias between the expected realised variance under the historical measure and the risk neutral probability introduces the concept of the risk premium. How does the market variance risk premium vary over time or look like in the future? Our work introduced a probabilistic modeling of the...

Information arrivals may drive investors to require immediacy, generating sudden liquidity demand across multiple price levels in limit order books. We document significant intraday changes in stock limit order book characteristics and liquidity beyond the best levels around scheduled and...

Think about a situation, where a financial institution has multiple option positions, each written on a different underlying asset, and the unexpected arrival of market-wide news shakes the markets. In the case of such a market-wide news arrival, all the volatility models on different...

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...