A significant Improvement In Mean-Reversion Strategy Performance

By exiting trades at the close that triggers a signal instead of the open of the next day, the annualized return of the MR5 mean-reversion strategy increases by 300 basis points with a simultaneous increase in win rate and decrease in maximum drawdown.

Exiting trades at the close is not always feasible or convenient since the exit signal is known only after the close and market-on-close orders must be entered at least 15 minutes before the close in the case of most exchanges and at least 10 minutes before in the case of direct orders to specific exchanges.

Although we can only be certain whether an exit order was generated at the close only after the closing price is available, in most cases if there are no fast market conditions automated strategies can handle that in the code and make certain assumptions if the market trades at a price that is sufficiently far away from the price that triggers the strategy exit signal.

The above solution is not practical for those who enter orders manually or for signal vendors that do not offer code to customers. In that case a projection of the minimum exit price is required and a LOC (Limit-on-Close) order must be placed in the case of a long-only strategy. The order will be executed if the closing price is at or better than the limit price.

However, knowing the limit price is not always trivial and may require an iterative solution to get it if there is no closed-form solution. For example, the price to affect a moving average crossover is easy to derive analytically but in some cases the strategy equations do not have an easy solution and the limit price must be computed using other methods.

We have implemented an iterative solution for determining the exit-on-close minimum price in the case of the MR5 (PSI5) strategy because the difference in performance between an exit at the close and an exit at the following open is significant. Below are the backtests, left exit at the open of the next day, right at the close of the day the exit signal is generated. Commission of $0.01/share is included for fully invested equity. Backtests are since inception of SPY to 01/05/2018.

Exit at next open

Exit this close

Performance comparison

Parameter Exit At Next Open Exit This Close
CAGR 8.84% 11.8%
Max. DD -26% -24.6
Sharpe 0.63 0.74
MAR 0.34 0.48
Win rate 71.4% 75.3%
Trades 507 567

By exiting at the close, CAGR increases by about 3% annually, max. drawdown decreases, Sharpe, MAR. win rate and the number of trades increase.

We will start providing the projected levels for LOC to our mean-reversion signal subscribers in the case of MR5 strategy starting with the next signal.

MR5 signals for SPY and UPRO are included in our Mean-reversion signal service. 

Disclaimer: The strategies are provided as educational trading tools for informational purposes only and do not constitute investment advice. We do not warrant the accuracy, completeness, fitness or timeliness for any particular purposes of any strategy. Under no circumstances the strategies should be treated as financial advice. Note that performance results are based on backtests.  Before subscribing please read our Disclaimer and Terms and Conditions.

Copyright notice: Any unauthorized copy, reproduction, distribution, publication, display, modification, or transmission of any part of this report is strictly prohibited without prior written permission.

This entry was posted in Trading Strategies and tagged , , , . Bookmark the permalink.

Leave a Reply