60 citations · 104 across the 6 of their papers we have counts for
6 papers
A Random-Matrix Criterion for Initializing Gated Recurrent Neural Networks
Tommaso Fioratti, Riccardo Marcaccioli, Francesco Casola
Proper weight initialization prior to training has historically been one of the key factors that helped kick off the deep learning revolution. Initialization is even more crucial i…
Exogenous and Endogenous Price Jumps Belong to Different Dynamical Classes
Riccardo Marcaccioli, Jean-Philippe Bouchaud, Michael Benzaquen
Synchronising a database of stock specific news with 5 years worth of order book data on 300 stocks, we show that abnormal price movements following news releases (exogenous) exhib…
Deep Reinforcement Learning for Active High Frequency Trading
Antonio Briola, Jeremy Turiel, Riccardo Marcaccioli +2
We introduce the first end-to-end Deep Reinforcement Learning (DRL) based framework for active high frequency trading in the stock market. We train DRL agents to trade one unit of…
Correspondence between temporal correlations in time series, inverse problems, and the Spherical Model
Riccardo Marcaccioli, Giacomo Livan
In this paper we employ methods from Statistical Mechanics to model temporal correlations in time series. We put forward a methodology based on the Maximum Entropy principle to gen…
Maximum Entropy approach to multivariate time series randomization
Riccardo Marcaccioli, Giacomo Livan
Natural and social multivariate systems are commonly studied through sets of simultaneous and time-spaced measurements of the observables that drive their dynamics, i.e., through s…
A parametric approach to information filtering in complex networks: The Pólya filter
Riccardo Marcaccioli, Giacomo Livan
The ever increasing availability of data demands for techniques to extract relevant information from complex interacting systems, which can often be represented as weighted network…