Bayesian Deep Learning for Accurate Characterisation of Uncertainties in Time Series Analysis
At alpha-i we are developing deep learning models for accurate characterisation of uncertainties in time series analysis. We achieve this by combining deep learning methodologies with powerful Bayesian formalism. The alpha-i deep learning network is able not only to make forecasts from time series but also to associate each prediction with a confidence level, which is derived from the information about the model and the data available. One of the key aspect of this Bayesian deep learning methodology is its aversion to over-fitting obtained thanks to the robust probabilistic inference framework. We are also developing novel Bayesian inference methodologies to significantly boost the online performance of our machinery.
Giacomo Mariotti has a Master’s degrees in Particle Physics from the University of Padova and in Quantitative Finance from Cass Business School. He worked for two years in risk management at RWE npower where he was the head quant of the hedging desk. In 2016 he was selected by Europe's best deep-tech startup accelerator Entrepreneur First, where he met Sreekumar Balan. Together they founded alpha-i, London based AI startup driving cutting edge research in the field of Bayesian Deep Learning applied to time-series analysis.