Quantifying instabilities in Financial Markets
April 18, 2017 Β· Declared Dead Β· π Physica A: Statistical Mechanics and its Applications
"No code URL or promise found in abstract"
Evidence collected by the PWNC Scanner
Authors
Bruna Amin GonΓ§alves, Laura Carpi, Osvaldo A. Rosso, Martin G. Ravetti, A. P. F Atman
arXiv ID
1704.05499
Category
q-fin.ST
Cross-listed
cs.IT
Citations
16
Venue
Physica A: Statistical Mechanics and its Applications
Last Checked
1 month ago
Abstract
Financial global crisis has devastating impacts to economies since early XX century and continues to impose increasing collateral damages for governments, enterprises, and society in general. Up to now, all efforts to obtain efficient methods to predict these events have been disappointing. However, the quest for a robust estimator of the degree of the market efficiency, or even, a crisis predictor, is still one of the most studied subjects in the field. We present here an original contribution that combines Information Theory with graph concepts, to study the return rate series of 32 global trade markets. Specifically, we propose a very simple quantifier that shows to be highly correlated with global financial instability periods, being also a good estimator of the market crisis risk and market resilience. We show that this estimator displays striking results when applied to countries that played central roles during the last major global market crisis. The simplicity and effectiveness of our quantifier allow us to anticipate its use in a wide range of disciplines.
Community Contributions
Found the code? Know the venue? Think something is wrong? Let us know!
π Similar Papers
In the same crypt β q-fin.ST
R.I.P.
π»
Ghosted
R.I.P.
π»
Ghosted
HATS: A Hierarchical Graph Attention Network for Stock Movement Prediction
R.I.P.
π»
Ghosted
A Robust Predictive Model for Stock Price Prediction Using Deep Learning and Natural Language Processing
R.I.P.
π»
Ghosted
Fast Training Algorithms for Deep Convolutional Fuzzy Systems with Application to Stock Index Prediction
R.I.P.
π»
Ghosted
Evolutionary dynamics of cryptocurrency transaction networks: An empirical study
R.I.P.
π»
Ghosted
Robust Analysis of Stock Price Time Series Using CNN and LSTM-Based Deep Learning Models
Died the same way β π» Ghosted
R.I.P.
π»
Ghosted
Language Models are Few-Shot Learners
R.I.P.
π»
Ghosted
PyTorch: An Imperative Style, High-Performance Deep Learning Library
R.I.P.
π»
Ghosted
XGBoost: A Scalable Tree Boosting System
R.I.P.
π»
Ghosted