Finemma
Research notes
New research on machine learning, forecasting and backtesting in finance, read and summarised by the Finemma team.
- Research digest
Research digest, 16 November 2026
This week's notes cover four preprints about evaluating AI and decision systems in finance beyond a single headline number. They look at compliance controls for LLM trading agents, run-to-run noise in a financial research agent, forecasts designed around a battery trading decision, and a credit collections benchmark with a known optimum.
- Insight
The trade-off between flexibility and interpretability
Every model choice trades flexibility against interpretability: the more complex the patterns a model can fit, the harder it is to see how it reaches a decision. Here is that trade-off, method by method, with a credit risk model as the running example.
- Insight
Interpretable or explainable? Not the same thing
"Interpretable" and "explainable" are often used as synonyms, but they describe two different ways of understanding a model. In finance, where decisions must be justified to clients, auditors and regulators, the difference matters.
- Research digest
Research digest, 13 November 2026
This week's notes cover four preprints. Each asks what is left of an apparent signal once real-world conditions are added: adversarial inputs, transaction costs, portfolio constraints, or an independent replication.
- Research digest
Research digest, 12 November 2026
This week's notes cover four preprints. Three of them are about the same question: does a model's apparent skill survive an honest test? The fourth looks at how the training environment shapes a hedging policy.
- Research digest
Research digest, 11 November 2026
This week's notes cover four preprints. Two are about evaluation hygiene, and one is about uncertainty in risk forecasts.
These notes summarise research for information only; they are not investment advice.