Search Results for author: Fabrizio Lillo

Found 30 papers, 5 papers with code

Why Are Learned Indexes So Effective?

1 code implementation ICML 2020 Paolo Ferragina, Fabrizio Lillo, Giorgio Vinciguerra

A recent trend in algorithm design consists of augmenting classic data structures with machine learning models, which are better suited to reveal and exploit patterns and trends in the input data so to achieve outstanding practical improvements in space occupancy and time efficiency.

Modelling shock propagation and resilience in financial temporal networks

no code implementations12 Jul 2024 Fabrizio Lillo, Giorgio Rizzini

Unlike the standard VAR, the model is a nonlinear function of the shock size and the IRF depends on the state of the network at the shock time.

CAESar: Conditional Autoregressive Expected Shortfall

1 code implementation9 Jul 2024 Federico Gatta, Fabrizio Lillo, Piero Mazzarisi

Building on this, we propose a new methodology named Conditional Autoregressive Expected Shortfall (CAESar), inspired by the CAViaR model.

Management regression

Online Learning of Order Flow and Market Impact with Bayesian Change-Point Detection Methods

no code implementations5 Jul 2023 Ioanna-Yvonni Tsaknaki, Fabrizio Lillo, Piero Mazzarisi

behavior within each regime; (ii) When examining the residuals, our model demonstrates good specification in terms of both distributional assumptions and temporal correlations; (iii) Within a given regime, the price dynamics exhibit a concave relationship with respect to time and volume, mirroring the characteristics of actual large orders; (iv) By incorporating regime information, our model produces more accurate online predictions of order flow and market impact compared to models that do not consider regimes.

Change Point Detection

A machine learning approach to support decision in insider trading detection

no code implementations6 Dec 2022 Piero Mazzarisi, Adele Ravagnani, Paola Deriu, Fabrizio Lillo, Francesca Medda, Antonio Russo

The first one uses clustering to identify, in the vicinity of a price sensitive event such as a takeover bid, discontinuities in the trading activity of an investor with respect to his/her own past trading history and on the present trading activity of his/her peers.

How Covid mobility restrictions modified the population of investors in Italian stock markets

no code implementations30 Jul 2022 Paola Deriu, Fabrizio Lillo, Piero Mazzarisi, Francesca Medda, Adele Ravagnani, Antonio Russo

There are thus indications that the lockdown, and more generally the Covid pandemic, created a sort of regime change in the population of financial investors.

Transient impact from the Nash equilibrium of a permanent market impact game

no code implementations1 May 2022 Francesco Cordoni, Fabrizio Lillo

We show that an implied transient impact arises from the Nash equilibrium between a directional trader and one arbitrageur in a market impact game with fixed and permanent impact.

From Zero-Intelligence to Queue-Reactive: Limit Order Book modeling for high-frequency volatility estimation and optimal execution

no code implementations24 Feb 2022 Tommaso Mariotti, Fabrizio Lillo, Giacomo Toscano

Building on this approach, in this paper we introduce three main innovations: (i) we use as data-generating process the Queue-Reactive model of the limit order book (Huang et al. (2015)), which - compared to the Zero-Intelligence model - generates more realistic microstructure dynamics, as shown here by using an Hausman test; (ii) we consider not only estimators of the integrated volatility but also of the spot volatility; (iii) we show the relevance of the estimator in the prediction of the variance of the cost of a simulated VWAP execution.

Information dynamics of price and liquidity around the 2017 Bitcoin markets crash

no code implementations17 Nov 2021 Vaiva Vasiliauskaite, Fabrizio Lillo, Nino Antulov-Fantulin

We study the information dynamics between the largest Bitcoin exchange markets during the bubble in 2017-2018.

Order flow and price formation

no code implementations2 May 2021 Fabrizio Lillo

I present an overview of some recent advancements on the empirical analysis and theoretical modeling of the process of price formation in financial markets as the result of the arrival of orders in a limit order book exchange.

Algorithmic Trading

Analysis of bank leverage via dynamical systems and deep neural networks

no code implementations11 Apr 2021 Fabrizio Lillo, Giulia Livieri, Stefano Marmi, Anton Solomko, Sandro Vaienti

We find that the parameters of a substantial fraction of banks lie in the dynamical core, and their leverage time series are consistent with a chaotic behavior.

Time Series Time Series Analysis

Estimating the Total Volume of Queries to a Search Engine

1 code implementation24 Jan 2021 Fabrizio Lillo, Salvatore Ruggieri

The observed volumes of sample queries are collected from Google Trends (continuous data) and SearchVolume (binned data).

On the equivalence between the Kinetic Ising Model and discrete autoregressive processes

no code implementations24 Aug 2020 Carlo Campajola, Fabrizio Lillo, Piero Mazzarisi, Daniele Tantari

Binary random variables are the building blocks used to describe a large variety of systems, from magnetic spins to financial time series and neuron activity.

Statistical Mechanics Econometrics Data Analysis, Statistics and Probability

Modelling time-varying interactions in complex systems: the Score Driven Kinetic Ising Model

1 code implementation30 Jul 2020 Carlo Campajola, Domenico Di Gangi, Fabrizio Lillo, Daniele Tantari

A common issue when analyzing real-world complex systems is that the interactions between the elements often change over time: this makes it difficult to find optimal models that describe this evolution and that can be estimated from data, particularly when the driving mechanisms are not known.

Time Series Analysis

Tail Granger causalities and where to find them: extreme risk spillovers vs. spurious linkages

no code implementations3 May 2020 Piero Mazzarisi, Silvia Zaoli, Carlo Campajola, Fabrizio Lillo

Identifying risk spillovers in financial markets is of great importance for assessing systemic risk and portfolio management.

Management Time Series +1

Instabilities in Multi-Asset and Multi-Agent Market Impact Games

no code implementations7 Apr 2020 Francesco Cordoni, Fabrizio Lillo

We consider the general problem of a set of agents trading a portfolio of assets in the presence of transient price impact and additional quadratic transaction costs and we study, with analytical and numerical methods, the resulting Nash equilibria.

Unveiling the relation between herding and liquidity with trader lead-lag networks

no code implementations24 Sep 2019 Carlo Campajola, Fabrizio Lillo, Daniele Tantari

We propose a method to infer lead-lag networks of traders from the observation of their trade record as well as to reconstruct their state of supply and demand when they do not trade.


Clusters of investors around Initial Public Offering

no code implementations31 May 2019 Margarita Baltakienė, Kęstutis Baltakys, Juho Kanniainen, Dino Pedreschi, Fabrizio Lillo

The complex networks approach has been gaining popularity in analysing investor behaviour and stock markets, but within this approach, initial public offerings (IPO) have barely been explored.

Crossover from linear to square-Root market impact

2 code implementations13 Nov 2018 Frédéric Bucci, Michael Benzaquen, Fabrizio Lillo, Jean-Philippe Bouchaud

Using a large database of 8 million institutional trades executed in the U. S. equity market, we establish a clear crossover between a linear market impact regime and a square-root regime as a function of the volume of the order.

Trading and Market Microstructure Statistical Mechanics

A dynamic network model with persistent links and node-specific latent variables, with an application to the interbank market

no code implementations30 Dec 2017 Piero Mazzarisi, Paolo Barucca, Fabrizio Lillo, Daniele Tantari

We propose a dynamic network model where two mechanisms control the probability of a link between two nodes: (i) the existence or absence of this link in the past, and (ii) node-specific latent variables (dynamic fitnesses) describing the propensity of each node to create links.

Corporate payments networks and credit risk rating

no code implementations21 Nov 2017 Elisa Letizia, Fabrizio Lillo

Aggregate and systemic risk in complex systems are emergent phenomena depending on two properties: the idiosyncratic risks of the elements and the topology of the network of interactions among them.

Social and Information Networks Risk Management 91D30, 05C82, 91G40, 68T05 91D30

Disentangling group and link persistence in Dynamic Stochastic Block models

no code implementations20 Jan 2017 Paolo Barucca, Fabrizio Lillo, Piero Mazzarisi, Daniele Tantari

We analytically and numerically characterize the detectability transitions of such algorithm as a function of the memory parameters of the model and we make a comparison with a full dynamic inference.

Community Detection

Modeling FX market activity around macroeconomic news: a Hawkes process approach

no code implementations23 May 2014 Marcello Rambaldi, Paris Pennesi, Fabrizio Lillo

We present a Hawkes model approach to foreign exchange market in which the high frequency price dynamics is affected by a self exciting mechanism and an exogenous component, generated by the pre-announced arrival of macroeconomic news.

Trading and Market Microstructure

How markets slowly digest changes in supply and demand

no code implementations4 Sep 2008 Jean-Philippe Bouchaud, J. Doyne Farmer, Fabrizio Lillo

In this article we revisit the classic problem of tatonnement in price formation from a microstructure point of view, reviewing a recent body of theoretical and empirical work explaining how fluctuations in supply and demand are slowly incorporated into prices.

Trading and Market Microstructure Statistical Mechanics Physics and Society

Cluster analysis for portfolio optimization

no code implementations1 Jul 2005 Vincenzo Tola, Fabrizio Lillo, Mauro Gallegati, Rosario N. Mantegna

We consider the problem of the statistical uncertainty of the correlation matrix in the optimization of a financial portfolio.

Physics and Society Other Condensed Matter Statistical Finance

Topology of correlation based minimal spanning trees in real and model markets

no code implementations25 Nov 2002 Giovanni Bonanno, Guido Caldarelli, Fabrizio Lillo, and Rosario N. Mantegna

We present here a topological characterization of the minimal spanning tree that can be obtained by considering the price return correlations of stocks traded in a financial market.

Statistical Mechanics

Cannot find the paper you are looking for? You can Submit a new open access paper.