Open Conference Systems, 50th Scientific meeting of the Italian Statistical Society

Font Size: 
Exploiting information network model based for financial forecasting
Giancarlo Nicola, Paola Cerchiello, Tomaso Aste

Last modified: 2018-05-17


In this contribution we aim at combining graphical models and neural network for predicting bank stock returns. We propose to leverage the information extracted from graphical models fitted on financial data timeseries as input features to a neural network to improve the predictive performance. We focus on the 74 largest listed U.S. banks over a period that spans from 2003 to 2017. We apply a recent and fast algorithm (LoGo) for the network estimation that allows us to calculate the banks' partial correlations network and relative indexes like mutual information and transfer entropy. The information obtained from the network are then leveraged as features in a Recurrent Neural Network and in other predictive models for comparison.


1. Barfuss Wolfram, Massara Guido Previde, Di Matteo T. and Aste Tomaso (2016) Parsimonious modeling with information filtering networks. Physical Review E, 94 (6). ISSN 1539-
2. Lauritzen, S. L. (1996) Graphical models. Oxford University Press
3. Whittaker J. (1990) Graphical models in applied multivariate statistics. Wiley Publishing

Full Text: PDF