Hi there, I'm Paolo Giudici, a professor of statistics here at the Department of Economics in University of Pavia. I'm also the coordinator of the periscope project, which is a large project dedicated to the learner, and respond to the impacts of the pandemic, and its socio-economic impacts in particular. Here we have a large group of about 16 statisticians, and data scientists, all worker in the area of trying to build statistical models based on data, that are aimed to measure the impacts, and the risks related to the pandemic, and its impact on the economy. In particular, we address both the issue of understanding the impact of the current pandemic, and the prediction of what the possible future impact could be in terms of both frequency and also on the economy at large. We do this looking both at the financial markets and financial prize in particular and the impact on the credit market, through the lens of credit rating and credit scoring. All this work is done by means of multivariate statistics models, and explainable machine learning models, in connection with the econometric models, that take into account the dependence of observations in time and space. The group, as I said before, is larger, it includes professors, postdoc researchers, and PhD students, all with different specialization altogether, we work in the several activities of the periscope. In particular, there is the one that is the object of this specific presentation that is about the building of multivariate network models, to measure the impacts of the pandemic on finance and financial technologies in particular. Financial technologies as we know, applications of finance, offer a machine learning and artificial intelligence. The idea of our group is to measure the opportunities, and the risks generated by financial technologies, trying to make them more sustainable, and in particular more inclusive of different people in different companies, particularly those that are not so well covered by the classic banking and capital markets. We also address the issue of making the applications of artificial intelligence sustainable in the sense that, they provide allocation credit to all sectors of the economy that are more sustainable, that is more environmentally safer and more fair from a social viewpoint. Hi there, this is Paola Cerchiello, from University of Pavia. I work with Paolo Giudici, and all the other guys within the periscope project on different fields, and different research areas. Specifically for what concerns the financial inclusion or financial constraint problems, we have been working on several papers trying to cope with the issue of assessing the impact of the pandemic on the financial sectors or economic sectors, mainly using my Bayesian graphical models or Bayesian graphical auto-regressive models. The main aim was to assess somehow the impact of the pandemic on the sectors, by leveraging some information that are daily available like for example, petitions of industries on the market, and some indicators of sentiment. The perception of the banks as captured by the audience still by the population in general. How population feel with regards to what's going on the market in general, and the daily life, of course. We have started some different effects on different sectors, and how they react to exogenous shocks. We discovered for example that the financial subsectors tend to be much more resilient compared to other sectors, like the consumer one, that is much more hit by external shocks. Since the graphical models can give you just one idea or one picture of what's going on, which tend to be more descriptive, we also investigate some ways of compounding several indicators, several measures, in just one unique measure, in order to use this information for different purpose, like for predicting some other quantitative economic figures. The idea was to discover, or to produce, or to make advantage of some principal component technique or in general, dimension reduction technique in order to produce syntactically indicators that compound several information. We apply this idea both on strictly related financial problems, but also to epidemiologic impact. We delivered an indicator, that is able to discover, give fact on the countries of shocks that are typically related to epidemiologic or disease in general issues. All these indicators can be then used as predictors for other problems like financial inclusion problems that are typical problems in topics that are also addressed by other colleagues of these groups. We work as a team so there are some of us working on producing sensitive enough and representative enough indicators, that they can then use and leveraged by other colleagues that maybe focused more on the prediction of the impact on the economic or financial sectors or as a further topic to address issues related to the sustainable finance in general, and to the risk related to the transition from a standard regular finance as we are all used to, to a more sustainable and real one. We try to explore all the different dimensions, and we elaborate the data in different alternative ways that at the end can be used all together, to produce more comprehensive models, and more reliable predictions. Thank you.