daggetk
1 posts
msg #96028
- Ignore daggetk |
9/5/2010 8:35:07 PM
Kevin, thanks for all the work you have done on this forum. I would like to re-produce your results. However, I can't seem to see the latest filter you are using. could you please point me to the latest filter? Thanks again.
|
Kevin_in_GA
4,599 posts
msg #96047
- Ignore Kevin_in_GA |
9/7/2010 6:36:49 AM
Sure thing:
|
Kevin_in_GA
4,599 posts
msg #96048
- Ignore Kevin_in_GA |
9/7/2010 6:39:43 AM
Here's the "mirror image" short version:
|
Kevin_in_GA
4,599 posts
msg #96049
- Ignore Kevin_in_GA |
9/7/2010 6:58:48 AM
I’ll be in London this week on business, with a fairly busy schedule. Back on Friday.
Futures are getting ugly today, so no planned trades.
The filters pulled up a couple of short candidates worth tracking however:
BCRD
KV-A
SNIC
PDE
ITMN
Only three long plays were generated:
BNE
AVNR
EUO
Can’t really track these as I usually do, so I’ll sit in cash for this week.
|
markd01
10 posts
msg #96680
- Ignore markd01 |
10/1/2010 8:50:25 PM
Great job, Kevin! Nice job backtesting your strategies, and doing public forward testing..
1) Have you tried setting your entry point to be a further intraday pullback of 3.5% to 7.0 % away from yesterday's close, as long as you can identify a support/resistance trendline? You'd have many unfilled orders, but the ones that do fill have much higher profits and lower drawdowns..
2) At portfolio level, is your whole strategy based on always being market neutral, meaning you'd need to have a short position for each long position at all times? Do you have any research that you could share that this is optimal? I always wanted to build market neutral portfolios too, but found that in reality I'd enter positions according to market conditions. For example, if your ultimate goal is to have 10 positions in a portfolio, 5 long and 5 short, you'd enter long positions as markets are oversold, and then enter short positions as markets are overbought.
3) Do you have backtest results that show that exiting after RSI(2) > 70 for longs and RSI(2) < 30 for shorts is not optimal, and a time based stop loss of holding one week at the most is better? I've been struggling to prove it, taking opportunity cost into account. For example, if I went long, my stock kept on dropping for a month, but eventually came back and broke even when RSI(2) > 70, I'd spend 30 days to earn 0%. Taking opportunity cost into account, I could have gotten out at say 10% loss after 10 days, but then traded two more positions with the same cash, each earning me more than 5%, in which case using a time based stop loss and accounting for opportunity cost might be the better option.
|
saratur
14 posts
msg #96701
- Ignore saratur |
10/3/2010 4:07:48 AM
Kevin - do you continue to follow the system ? Any new conclusions?
|
Kevin_in_GA
4,599 posts
msg #96702
- Ignore Kevin_in_GA |
10/3/2010 10:22:23 AM
Sorry for the lack of recent posts - I have been looking at some new software that is pretty slick (StrataSearch, free fully functional demo available at www.stratasearch.com). It generates millions of combinations of different indicators and backtests them against any set of stocks and time frames the user chooses. Very fast, and I have been evaluating several filters that it has generated.
This approach is less effective of late, due to the high correlation between stocks (upwards of 90% of all stocks move in the same direction each day, making a long/short strategy very challenging to execute profitably).
As I had indicated at the onset, this was an approach I wanted to evaluate and would paper trade for 3 months or so. It did well during July, a little poorer in August, and even less well in September as the stock correlation kept going higher and higher. It crushed the market in overall return early on (from the start on 6/28 through 8/13 it netted 16.3% return versus only 0.7% for the SPY buy and hold) and I think I only had 2 weeks at a fractional percentage loss out of 10 total.
In all honesty I will not be updating this thread any more - I think the filters are good, they trade profitably, and the overall volatility is much less than the market as a whole. Happy to share them with the SF community and hope that others use (and improve upon) them as time goes on.
|
wkloss
231 posts
msg #96741
- Ignore wkloss |
10/5/2010 11:15:33 AM
Kevin,
You wrote
"I think the filters are good"
Did you mean the Connor's filters, the Stratasearch filters or both?
This was very educational and I hope you start some new topics soon.
bill
|
Kevin_in_GA
4,599 posts
msg #96744
- Ignore Kevin_in_GA |
10/5/2010 1:34:26 PM
I was referring to the filters used in this thread. Also, it makes sense to go dollar-neutral if possible (except for today, when everything went up).
As to the Stratasearch filters, I have focused on developing "all-long" filters to date. The ability for the program to backtest massive numbers of indicator combinations is really impressive.
Here's one I pulled from a recent optimization run
Exit when either the MA(7) crosses above the MA(40) or when the rmi(4,14) crosses above 45.
Backtest results for the last 4 months (arguably some of the hardest months to trade profitably given the ups and downs seen):
There were 149 total stocks entered. Of those, 133 or 89.26% were complete and 16 or 10.74% were open.
Of the 133 completed trades, 123 trades or 92.48% resulted in a net gain.
Your average net change for completed trades was: 4.60%.
The average draw down of your approach was: -4.40%.
The average max profit of your approach was: 6.19%
The Reward/Risk ratio for this approach is: 13.06
Annualized Return on Investment (ROI): 94.86%, the ROI of ^SPX was: 10.33%.
The stats for this simple filter are really impressive, and there's no way I would have come up with this specific combination.
I'll post a series of these for everyone to evaluate (at least those that can be readily translated into SF code).
Kevin
|
einok
msg #100440
- Ignore einok |
4/27/2011 12:41:23 AM
Hi Kevin,
How exactly is this a long filter?
market is S&P 500
close above 1
average volume(20) above 200000
MA(7) below MA(40)
rmi(4,14) crossed below 89
Exit when either the MA(7) crosses above the MA(40) or when the rmi(4,14) crosses above 45.
I see the exit, but what is then entry? When MA(7) below MA(40) and
rmi(4,14) crossed below 89? That seems short to me.
Are you working on any other filters with stratasearch?
|