Financial Engineering Workshops - Stefano Iabichino

Abstract: In finance, valuation must obey law; conventional AI risks economic hallucination, distorting pricing, hedging, and tail-risk. Rather than applying AI to finance and patching arbitrage violations ex post, we refound neural networks on asset pricing first principles. The result is the first finance-native neural network, in which neurons encode market states, and Markovian Activation Functions turn the First Fundamental Theorem of Finance into a binding computational constraint. Applied to real-world QIS portfolios, it enables XVA-style forward-looking strategy design, learning markets in 8 minutes and simulating 100,000 scenarios across 800 layers in 80 seconds on a MacBook Pro. Rooted in pricing axioms, AI sheds its black-box mystique to deliver coherent valuation, robust risk diagnostics, and strategy innovation in a consistent engine where every neuron obeys the immutable laws of finance.

Bio: Stefano Iabichino is a Strategy Quant in UBS’s Quantitative Investment Solutions team. He previously worked at J.P. Morgan in Counterparty Credit Risk and as a Quant Researcher at Global Valuation Ltd. His research focuses on finance-native AI, QIS, XVA, and optimal funding policy, with several publications in these areas. He holds a PhD in Quantitative Finance from Tor Vergata University, Rome.

Faculty Events | Website | View More Events

Contact the organizers