Backtesting is one of the most important parts of any trading system. It is done by reconstructing, with historical data, trades that would have taken place in the past using rules based on a given strategy.
Rule 1
Always take into consideration the broad market trends in the time frame a given strategy was tested. For a quick example, if the strategy was only backtested from 1999 to 2000, it may not perform well in a bear market.
You would be the wiser to backtest over a long time frame encompassing several different types of market conditions.
Rule 2
Always consider the industry or sector in which backtesting took place. For instance, if a broad market system is tested with a universe consisting of tech stocks, it may fail to do so in different sectors.
As a general rule, if a strategy is targeted toward a specific genre of stock, you should limit the universe to that genre. In all other cases, maintain a large universe for testing purposes.
Rule 3
Volatility measures are extremely important to consider in developing a trading system. This is particularly true for leveraged accounts, which are always at risk of margin calls if their equity slips lower than a specific threshold.
Traders should always try to keep volatility low to decrease risk and enable easier transition in and out of a given stock.
Rule 4
The average number of bars held is also very important to watch when developing a trading system. Although most backtesting software includes commission costs in the final calculations that does not mean that you should ignore this data.
If you can, you can raise the number of your bars held to lower your commission costs and improve your overall return.
Rule 5
Exposure is a double-edged sword. Higher exposure can lead to higher profits or higher losses. Meanwhile, decreased exposure means lower profits or lower losses.
Generally, it’s a good idea to keep exposure lower than 70 percent to diminish risk and make way to easier transition in and out of a given stock.
Rule 6
You can use the average gain/loss statistic combined with wins to losses ratio to determine optimal position sizing and money management using techniques like the Kelly Criterion. Traders can take larger positions and reduce commission costs by increasing their average gains and increasing their wins to losses ratios.
Rule 7
Annualized return is used as a tool to benchmark a system’s returns against other investment venues. It is important not only to look at the overall annualized return but also to take into account the increased or decreased risk.
This can be done by looking at the risk-adjusted return, which takes into consideration various risk factors. Before a trading system is adopted, it must outperform all other investment venues at equal or less risk.
Rule 8
Backtesting customization is extremely important. Many backtesting applications have input for commission amounts, round (or fractional) lot sizes, tick sizes, margin requirements, interest rates, slippage assumptions, position sizing rules, same-bar exit rules, (trailing) stop settings, and much more.
To get the most accurate backtesting results, it is important to tune these settings to imitate the broker to be used when the system goes live.
Rule 9
Backtesting can sometimes lead to what is usually called over-optimization. This is a condition where performance results are tuned so high to the past that they are no longer as accurate in the future. It is generally a good idea to implement rules that apply to all stocks or a select set of targeted stocks, and are not optimized to the extent the rules are no longer understandable by the creator.
Comments