From Forecast to Position
A model that predicts returns has produced information, not money. The translation is sizing, and it is a place where a mediocre forecast sized well beats a good forecast sized badly. Interviewers probe it because it separates candidates who have run strategies from those who have graded classifiers.
Risk first, dollars second
The primitive is not "how many shares" but "how much risk." Positions are set to contribute a target volatility, which makes a book comparable across assets and stable across regimes: a position in a 40%-volatility name is held at a quarter the dollar size of one in a 10%-volatility name for the same risk. Scaling the whole book to a portfolio volatility target then keeps risk roughly constant as opportunities come and go.
Conviction scales within that frame: sizing proportional to the forecast's strength divided by its variance, so a strong clean signal takes more risk than a weak noisy one. This is the practical content of the Kelly intuition: optimal size grows with edge and shrinks with variance.
The rest of this lesson is for subscribers
Unlock every lesson in Research Validation and Backtesting, and every other premium course.
Subscribe to continueTest your knowledge
Keep reading Research Validation and Backtesting
21 lessons in this course, and every other premium course, on one subscription.
- Every lesson in every course, with the worked examples and interactive simulators
- Graded questions on every lesson, with explanations for the wrong answers as well as the right one
- The trainers, timed assessments and brainteaser library that go with them