Given a gated probability that the primary side is correct, the event classifier must become a position. This note adapts the bet-sizing lesson: Kelly for binary bets, fractional Kelly as the practical compromise, and the probability-to-signed-size map. It does not re-derive meta-labeling (already covered) or invent sizing rules beyond that source.
Learning objectives. By the end of this note you should be able to:
- compute for a binary bet when is trusted;
- apply fractional Kelly as the source states it;
- map to via the source's Normal-CDF construction;
- produce a sizing ticket for a fixture event.
In this lesson
- Probability to fraction of risk
- The decision for the event book
- Deliverable: position map
Before you start
The full lesson, with worked examples and exercise solutions, is for members.
Read the full lessonNew to SelfMadeQuant.com? See membership options or browse the Financial Machine Learning syllabus.