Matteo Iacopini

Modern economic analyses require new models to study increasingly fine-grained interrelations based on increasingly complex data sources. Early dynamic economic analyses have mostly been limited to only studying univariate time series, which can be represented as a single sequence (or vector) of values. Most contemporary analyses use more complicated data with both time series and cross-sectional dimensions, such as panels of key macroeconomic figures, for many countries over time. Such data can be represented as a (2-dim) matrix.

Recently, more complex data structures have rapidly emerged, requiring higher dimensional storage objects. As an example, a data set consisting of a time series (1st dimension) of the exposures of banks (2nd dim) to other banks (3rd dim) in several markets (bonds, equity; 4th dim) and for different maturities (5th dim). The storage object for such high-dimensional data sets is a generalization of a matrix, called a tensor. Models for tensor data have applications to policy-relevant questions for central banks and financial regulators, including forecasting multi-country, multi-market interest rate term structures for the evaluation of monetary policy effectiveness, and nowcasting multi-country economic activity in the heterogeneous European context.

Tensor data are highly topical, however, in econometrics their use and the development of tensor models is very scant and almost exclusively limited to static tensors. The STEADY project fills this gap by developing novel statistical methods for time series of tensor data that account for the typical non-linear and dynamic features of economic data in a computationally feasible way. The project has two main research directions. One is the development of a general class of dynamic time-series models, which merge the linear tensor time series literature and the score-driven time-varying parameter approach based on the Generalized Autoregressive Score (GAS) model. The other contribution consists in the development of a new tensor-based compression technique for many economic time series, the tensor dynamic factor model.

Project Team

Principal Investigator: Matteo Iacopini
Supervisor: Siem Jan Koopman and André Lucas
Host institution: Vrije Universiteit Amsterdam

Other Journal Publications

1. Billio, M., Casarin, R. and Iacopini, M. (2022), "Markov Switching Tensor Regression for Time-varying Networks", Journal of the American Statistical Association (forthcoming) -- (article)
2. Billio, M., Casarin, R., Iacopini, M. and Kaufmann, S. (2023), "Bayesian dynamic tensor regression", Journal of Business and Economic Statistics, 41(2):429--439 -- (article)
3. Iacopini, M., Ravazzolo, F. and Rossini, L. (2023), "Proper scoring rules for evaluating density forecasts with asymmetric loss functions", Journal of Business and Economic Statistics, 41(2):482--496 -- (code; article)
4. Billio, M., Casarin, R., Costola, M. and Iacopini, M. (2022), "Matrix-variate Smooth Transition Models for Temporal Networks", in Arashi, M., Bekker, A., Che, D., and Ferreira, J., Innovations in Multivariate Statistical Modeling: Navigating Theoretical and Multidisciplinary Domains, pages 137--167, Springer Emerging Topics in Statistics and Biostatistics
5. Billio, M., Casarin, R., Costola, M. and Iacopini, M. (2021), "COVID-19 spreading in financial networks: A semiparametric matrix regression model", Econometrics and Statistics, (forthcoming) -- (article)
6. Costola, M., Iacopini, M. and Santagiustina, C.R.M.A. (2021), "On the "mementum" of meme stocks", Economics Letters, 207, 110021 -- (article)
7. Billio, M., Casarin, R., Costola, M. and Iacopini, M. (2021), "A matrix-variate t model for networks", Frontiers in Artificial Intelligence 4, 49 -- (article)
8. Iacopini, M. and Santagiustina, C.R.M.A. (2021), "Filtering the intensity of public concern from social media count data with jumps", Journal of the Royal Statistical Society: Series A, 184:1283--1302 -- (article)

Working papers

1. Iacopini, M., Koopman, S.J. and Lucas, A. (20XX), "On Tensor state-space models"
2. Iacopini, M., Poon, A., Rossini, L. and Zhu, D. (20XX), "Bayesian Mixed-Frequency Quantile Vector Autoregression: Eliciting tail risks of Monthly US GDP" -- (working paper)
3. Bianchi, D., Iacopini, M. and Rossini, L. (20XX), "Stablecoins and Cryptocurrency Returns: Evidence from large Bayesian VARs" -- (working paper)

Top

Conferences

• 12th ESOBE - European Seminar on Bayesian Econometrics Annual Workshop.
  Salzburg, Austria -- 8-9 September 2022
• IAAE 2022 - Annual Conference of the International Association of Applied Econometrics.
  London, United Kingdom -- 21-24 June 2022
• 5th Workshop on High-Dimensional Time Series in Macroeconomics and Finance.
  Wien, Austria -- June 9-10, 2022
• 3rd IWEEE - International Workshop on Econometrics and Empirical Economics.
  Rimini, Italy -- January 20-21, 2022
• CFENetwork - International Conference on Computational and Financial Econometrics.
  London, United Kingdom -- December 18-20, 2021
• 4th Annual Workshop on Financial Econometrics.
  Örebro, Sweden -- 15-16 November 2021
• 11th ESOBE - European Seminar on Bayesian Econometrics Annual Workshop.
  Madrid, Spain -- 2-3 September 2021
• IAAE 2021 - Annual Conference of the International Association of Applied Econometrics.
  Rotterdam, The Netherlands -- 22-25 June 2021
• BISP-12 - 12th Workshop on Bayesian Inference in Stochastic Processes.
  Milan, Italy -- 27-28 May 2021
• Dynamic Econometrics Conference.
  Virtual -- 18-19 March 2021
• 31st EC2 Conference on High dimensional modeling in time series.
  Paris, France -- 11-12 December 2020

Seminars

• Invited Speaker at "Bayesian Nonparametrics Networking workshop".
  Nicosia, Cyprus -- 25-29 April 2022
• Seminar at Department of Economics, Ca’ Foscari University of Venice.
  Venice, Italy -- 2 February 2022

Visiting periods

• Paris Lodron University of Salzburg, Department of Economics.
  Slazburg, Austria -- June 2022
• University of Milan, Department of Economics, Management, and Quantitative Methods.
  Milan, Italy -- May/June 2022
• Polytechnic University of Milan, Department of Mathematics.
  Milan, Italy -- November 2021
• University of Milan, Department of Economics, Management, and Quantitative Methods.
  Milan, Italy -- October 2021

Top