A strategy for automated trading is proposed, based on the assumption that dynamics of underlying asset shows evidence of mean reversion, similarly to Ornstein-Uhlenbeck process.

In order to describe the quantitative characteristics of the projected return of the strategy, the explicit expression for the running maximum of the Ornstein-Uhlenbeck process stopped at maximum drawdown is derived. The stopping rule based on maximum drawdown is essential to the proposed version of the strategy since it is equipped with trailing stop, which is equivalent to stopping at maximum drawdown from running maximum of the return process.

The derived characteristics of the proposed strategy are compared with the observed ones, as provided via backtesting in application to foreign exchange markets trading. Foreign exchange markets are selected as a base for backtesting for a number of reasons such as accessibility and consistency of data.

Good consistency of results obtained via backtesting confirm applicability of the proposed strategy to foreign markets trading and thus implicitly also indicate the presence of mean reversion on these markets.

Since the presence of mean reversion is an important part of the strategy’s concept, a separate section in devoted to discussions of evidence of mean reversion property on various markets, with literature review. As a conclusion, it is noted that applicability of the proposed strategy also extends to other types of financial markets and not restricted to foreign exchange markets on which the strategy was initially backtested.