Friday, September 13, 2013

Updated Intraday Trend Systems

Having gone over the counter trend approach and finding I could not produce good results on any system, I turned my attention to the systems which try to capture some part of the intraday trend. A simple system was developed which uses the same entry methods as always. The system was optimized for one 18 month time period selected from the years 2000 through 2012 (no 2013 data). The optimized strategy was then applied to historic data from 07.01.1999 through 09.13.2013. Below is the chart from the TradeStation performance report.

This above equity curve is based on data which is 90% out of sample and using $10/rt commissions and $25/rt slippage. This is a reversing strategy, but it also has stops and will stop trading if the daily loss exceeds a loss target. With a 1.15 profit factor, this is not a particularly compelling strategy, but it certainly passes the first and most important test of being able to produce positive returns outside of the design period.

Next the daily returns from the strategy are screened with a regression filter. The purpose of the filter is to determine whether a day is a good trading day before the day begins. These calculation are all done in an Excel spreadsheet. After filtering the trades, the equity curve looks like this:

The regression filtering in this case is done on an two year walk-forward basis. The regression filter is applied to each calendar year based on filter criteria from the preceding two years. For year 2001, it is only one year because the only trade history available is the year 2000. After that, it steps forward two years at a time. The backtest results has no losing years. Most importantly, the current year, 2013 performance is up about $5K per contract and it is entirely based on strategy design which does not include any data for the current year.

This looks good, but it's still all history and hypothetical and experience teaches us that (1) prior performance whether real or hypothetical is go guarantee of future results and (2) returns are much more likely to be lower than higher.

The next step is to begin reporting results going forward on the website, but I expect this to replace nearly everything that is on the current website as far as daytrading systems for the ES e-mini.

No comments:

Post a Comment