Optimal Trading Strategies for Expected Return and Information Ratio

Summary

The paper presents a general framework for deriving an optimal trading strategy from a historical indicator. It constructs one strategy intended to maximize expected return and a separate strategy intended to maximize the information ratio. The expected-return optimum can be implemented directly or used as a benchmark for judging other strategies built from the same indicator. This gives researchers a way to compare a proposed strategy with a theoretically optimal alternative under the framework’s assumptions.

The document reports that when the traded security’s return is near zero and correlations are reasonable, the performance gap between the two optima is economically small. As correlation approaches one, however, the expected-return-maximizing strategy approaches an information ratio of 1.32, while the information-ratio-maximizing strategy’s ratio grows without bound. The excerpt does not specify the framework’s assumptions, derivation, or empirical validation, so these conclusions should be understood within the stated model rather than as general realized-performance guarantees.

Key ideas

• The framework derives a strategy that maximizes expected return for a given historical indicator.
• It separately derives a strategy that maximizes the information ratio.
• The expected-return optimum can serve as a benchmark for evaluating other strategies using the same indicator.
• The document says the performance difference is small near zero security returns under reasonable correlations.
• As correlation approaches one, the two optimization objectives produce sharply different information-ratio behavior.

Tags

# Constructing the Best Trading Strategy: A New General Framework


# Constructing the Best Trading Strategy: A New General Framework









We introduce a new general framework for constructing the best trading strategy for a given historical indicator. We construct the unique trading strategy with the highest expected return. This optimal strategy may be implemented directly, or its expected return may be used as a benchmark to evaluate how far away from the optimal other proposed strategies for the given indicators are. Separately, we also construct the unique trading strategy with the highest information ratio. In the normal case, when the traded security return is near zero, and for reasonable correlations, the performance differences are economically insignificant. However, when the correlation approaches one, the trading strategy with the highest expected return approaches its maximum information ratio of 1.32 while the trading strategy with the highest information ratio goes to infinity.

Shown in full with attribution under the source's licence. Licence: abstract CC0

This summary was written by Stratmill's research agent from the original; it is not a copy of the source.