Explainable AI for financial risk
Risk models built to be audited rather than believed: auditable components, traceable signals, documented failure cases.
Quantitative research that shows its limits
Independent research at the intersection of AI, algorithmic trading and sustainable finance. Open data and clearly stated limitations.
Simulated forecast paths with quantile bands. This visualises the kind of uncertainty every paper here explicitly spells out.
Latest paper · 2026
The Efficiency Trap: Measurable Ex Post, Not Capturable Ex Ante
Selected papers
View all publications →2026
The Efficiency Trap: Measurable Ex Post, Not Capturable Ex Ante
This study consolidates and extends the contract-level efficiency analysis of Bixhili (2026) on an expanded frozen dataset of 420 resolved Kalshi contracts, up from 244.
Markets and trading
2026
Contract-Level Informational Efficiency in Prediction Markets: Measurable Ex Post, Not Predictable Ex Ante — Evidence from 244 Kalshi Markets
I study informational efficiency at the level of the individual contract in prediction markets, using a frozen dataset of 244 resolved Kalshi markets (21 distinct events, 2024–2026) in high-emotion categories.
Markets and trading
2026
Bridging the Green Tech Funding Gap: An AI-Driven Risk Assessment Framework — Evidence from the OBF project
The transition to a sustainable economy relies heavily on innovative environmental technologies.
AI and risk, Sustainable finance
Three questions, one method
Different markets, same discipline: state the assumptions, publish the materials, and write down where the result stops holding.
Algorithmic trading and prediction markets
What survives contact with real execution, and what market prices know that models do not.
Sustainable finance
Risk assessment for green technology, where the dominant uncertainty is policy, not price history.
The limits are part of the result
A finding you cannot bound is an anecdote. Every paper on this site carries a limitations section beside the abstract: sample, assumptions, and the claims the data cannot support. Readers should not have to reverse-engineer what a result does not say.
I make the limits visible.
Recent
NewsNov 2, 2026
The Efficiency Trap: Why Your Trading Strategy’s “Average” Return Is a Lie
Oct 30, 2026
OBF project registered on OSF and featured in Florence
Oct 28, 2026
Featured in an industry roundup on the NBA and prediction markets
Working on a problem in this space?
Collaborations, seminars and consulting around explainable risk models and market research.