Present expectations for artificial intelligence rely on the idea that the vast quantity of data that is continuously accumulated can be used to train machines that will become capable of modelling and predicting future behaviours of complex systems such as markets and societies. However, the broadly widened observation space, created by the abundance of data, generates new challenges concerning the construction of reliable predictive models that use a large number of variables but can be estimated from a limited number of observations only.
I will present machine learning methodologies based on the combination of information filtering networks and probabilistic modelling that can produce meaningful models which are capable to make reliable forecasts even in practical cases where uncertainty is present, statistical stability is poor, time series are short, and no reliable training sets are available.
Tomaso Aste is professor of Complexity Science at UCL Computer Science Department. A trained Physicist, has substantially contributed to research in complex structures analysis, financial systems modelling and machine learning. He is also an expert in the application of Blockchain Technologies to domains beyond digital currencies. He is Scientific Director of the UCL Centre for Blockchain Technologies; Head of the Financial Computing and Analytics Group; Programme Director of the MSc in Financial Risk Management; Vice-Director of the Centre for doctoral Training in Financial Computing & Analytics; Member of the Board of the ESRC LSE-UCL Systemic Risk Centre. Prior to UCL he hold positions in UK and Australia. He is advising and consulting for financial institutions, banks and digital-economy startups.