1 code implementation • 14 Mar 2024 • Antonio Briola, Silvia Bartolucci, Tomaso Aste
We exploit cutting-edge deep learning methodologies to explore the predictability of high-frequency Limit Order Book mid-price changes for a heterogeneous set of stocks traded on the NASDAQ exchange.
no code implementations • 23 Oct 2023 • Yuanrong Wang, Antonio Briola, Tomaso Aste
Following the seminal work of Markowitz, optimal asset allocation can be computed using a constrained optimization model based on empirical covariance.
1 code implementation • 20 Oct 2023 • Yufei Gu, Xiaoqing Zheng, Tomaso Aste
Double descent presents a counter-intuitive aspect within the machine learning domain, and researchers have observed its manifestation in various models and tasks.
1 code implementation • 26 Aug 2023 • Antonio Briola, Yuanrong Wang, Silvia Bartolucci, Tomaso Aste
Deep learning methods have demonstrated outstanding performances on classification and regression tasks on homogeneous data types (e. g., image, audio, and text data).
no code implementations • 21 Jul 2023 • Maxime L. D. Nicolas, Adrien Desroziers, Fabio Caccioli, Tomaso Aste
We investigate the response of shareholders to Environmental, Social, and Governance-related reputational risk (ESG-risk), focusing exclusively on the impact of social media.
1 code implementation • 27 Jun 2023 • Yuanrong Wang, Antonio Briola, Tomaso Aste
The rapid progress of Artificial Intelligence research came with the development of increasingly complex deep learning models, leading to growing challenges in terms of computational complexity, energy efficiency and interpretability.
no code implementations • 22 Feb 2023 • David Vidal-Tomás, Antonio Briola, Tomaso Aste
This paper investigates the causes of the FTX digital currency exchange's failure in November 2022.
1 code implementation • 19 Feb 2023 • Antonio Briola, Tomaso Aste
In this paper, we introduce a novel unsupervised, graph-based filter feature selection technique which exploits the power of topologically constrained network representations.
1 code implementation • 15 Aug 2022 • Danial Saef, Yuanrong Wang, Tomaso Aste
The increasing adoption of Digital Assets (DAs), such as Bitcoin (BTC), rises the need for accurate option pricing models.
no code implementations • 28 Jul 2022 • Antonio Briola, David Vidal-Tomás, Yuanrong Wang, Tomaso Aste
We quantitatively describe the main events that led to the Terra project's failure in May 2022.
no code implementations • 7 Jun 2022 • Antonio Briola, Tomaso Aste
We investigate logarithmic price returns cross-correlations at different time horizons for a set of 25 liquid cryptocurrencies traded on the FTX digital currency exchange.
no code implementations • 8 Mar 2022 • Yuanrong Wang, Tomaso Aste
We propose an end-to-end architecture for multivariate time-series prediction that integrates a spatial-temporal graph neural network with a matrix filtering module.
no code implementations • 31 Dec 2021 • Yuanrong Wang, Tomaso Aste
Market conditions change continuously.
no code implementations • 26 Oct 2021 • Jeremy Turiel, Tomaso Aste
Flash crashes in financial markets have become increasingly important attracting attention from financial regulators, market makers as well as from the media and the broader audience.
no code implementations • 26 Oct 2021 • Jeremy D. Turiel, Tomaso Aste
With the rise of computing and artificial intelligence, advanced modeling and forecasting has been applied to High Frequency markets.
no code implementations • 16 Jun 2021 • Isobel Seabrook, Fabio Caccioli, Tomaso Aste
We present a novel methodology to quantify the "impact" of and "response" to market shocks.
no code implementations • 28 Mar 2021 • Pier Francesco Procacci, Tomaso Aste
Portfolio optimization approaches inevitably rely on multivariate modeling of markets and the economy.
1 code implementation • 18 Jan 2021 • Antonio Briola, Jeremy Turiel, Riccardo Marcaccioli, Alvaro Cauderan, Tomaso Aste
The training is performed on three contiguous months of high frequency Limit Order Book data, of which the last month constitutes the validation data.
no code implementations • 16 Sep 2020 • Jeremy D. Turiel, Paolo Barucca, Tomaso Aste
We observe long memory in the evolution of structures from correlation filtering, with a two regime power law decay in the number of persistent simplicial complexes.
1 code implementation • 12 Jul 2020 • Antonio Briola, Jeremy Turiel, Tomaso Aste
The present work addresses theoretical and practical questions in the domain of Deep Learning for High Frequency Trading.
no code implementations • 10 May 2020 • Tomaso Aste
A methodology to perform topological regularization via information filtering network is introduced.
no code implementations • 14 Apr 2020 • Tomaso Aste
In the study of systemic risk in a financial system, the multivariate conditional probability distribution can be used for stress-testing by quantifying the propagation of losses from a set of `stressing' variables to another set of `stressed' variables.
no code implementations • 17 Oct 2019 • Jeremy Turiel, Tomaso Aste
We observe long-memory processes in these structures in the form of power law decays in the number of persistent motifs.
1 code implementation • 3 Jul 2019 • Jeremy D. Turiel, Tomaso Aste
Logistic Regression and Support Vector Machine algorithms, together with Linear and Non-Linear Deep Neural Networks, are applied to lending data in order to replicate lender acceptance of loans and predict the likelihood of default of issued loans.
Risk Management General Finance
no code implementations • 6 May 2019 • Guido Previde Massara, Tomaso Aste
Through this move the decomposability and calculation of scores is performed incrementally at the variable (rather than edge) level, and this provides better computational performance and an intuitive application of multivariate statistical tests.
1 code implementation • 3 Mar 2019 • Tomaso Aste
The study of the causality structure reveals a causality network that is consistently related with the correlation structures and shows that both prices cause sentiment and sentiment cause prices across currencies with the latter being stronger in size but smaller in number of significative interactions.
Statistical Finance Physics and Society Trading and Market Microstructure
no code implementations • 26 Nov 2018 • Thársis T. P. Souza, Tomaso Aste
We demonstrate that future market correlation structure can be predicted with high out-of-sample accuracy using a multiplex network approach that combines information from social media and financial data.
Statistical Finance
no code implementations • 13 Jul 2018 • Pier Francesco Procacci, Tomaso Aste
In another experiment, with again one hundred log-returns and two states, we demonstrate that this procedure can be efficiently used to forecast off-sample future market states with significant prediction accuracy.
1 code implementation • 15 Jun 2016 • Nicoló Musmeci, Vincenzo Nicosia, Tomaso Aste, Tiziana Di Matteo, Vito Latora
We propose here a multiplex network approach to investigate simultaneously different types of dependency in complex data sets.
Physics and Society Computational Engineering, Finance, and Science Statistical Finance
no code implementations • 23 Feb 2016 • Wolfram Barfuss, Guido Previde Massara, T. Di Matteo, Tomaso Aste
We also discuss performances with sparse factor models where we notice that relative performances decrease with the number of factors.
no code implementations • 18 Jan 2016 • Thársis T. P. Souza, Tomaso Aste
Online social networks offer a new way to investigate financial markets' dynamics by enabling the large-scale analysis of investors' collective behavior.
Statistical Finance Computers and Society Data Analysis, Statistics and Probability Computational Finance
no code implementations • 3 Jul 2015 • Olga Kolchyna, Tharsis T. P. Souza, Philip Treleaven, Tomaso Aste
We present a new ensemble method that uses a lexicon based sentiment score as input feature for the machine learning approach.
no code implementations • 10 May 2015 • Guido Previde Massara, T. Di Matteo, Tomaso Aste
TMFG uses as weights any arbitrary similarity measure to arrange data into a meaningful network structure that can be used for clustering, community detection and modeling.
no code implementations • 26 Jun 2009 • Won-Min Song, T. Di Matteo, Tomaso Aste
We construct a partial order relation which acts on the set of 3-cliques of a maximal planar graph G and defines a unique hierarchy.
Geometric Topology