You are using an out of date browser. It may not display this or other websites correctly.
You should upgrade or use an alternative browser.
You should upgrade or use an alternative browser.
System Development with acrary
- Thread starter acrary
- Start date
- Status
- Not open for further replies.
Quote from Walther:
I would like to hear more about what do you mean by a strategic vision ? I do not want to jump to conclusion but do I smell some forward projecting around here ?
You will when I start on building a system from scratch. No forward projecting here. It'll mostly be like "it's so obvious how come I didn't think of that?"
Quote from acrary:
For the MonteCarlo work I've written my own routines. I don't know of any software that simulates a non-normal trading type of distribution. The fat tails can make a big difference in the overall profit/(loss).
This might be some software that does (not sure if this is what you are referring to, though). The program is @risk
"Define Uncertainty with Ease
Choosing which @RISK distribution function to use for a cell containing uncertain values doesn't have to be complicated. @RISK comes with RISKview - a built-in distribution viewer that less you preview various distributions before selecting them. You can choose distributions from a gallery of thumbnail distribution pictures, and then watch as @RISK builds a graph of the distribution for you while you enter your parameters. "
http://www.palisade.com/risk/overview.asp
http://www.palisade.com/images/products/risk45/3defdistpopup.gif
Jonathan
Yes as I mentioned in my previous post. "@Risk" is a good program. Palisade has (or used to have) a student version available for less than $100. Adapts to various distributions including fat tails.
Also comes with a nice training manual (if a little brief). definitely the best of the class.
Steve
Also comes with a nice training manual (if a little brief). definitely the best of the class.
Steve
That will be great! I love to get humbled.Quote from acrary:
You will when I start on building a system from scratch. No forward projecting here. It'll mostly be like "it's so obvious how come I didn't think of that?"
I have this movie in my head where you are sitting in your garden house and picking your notes from a shelf, deciding what to post..
Thanks acrary for this awesome thread. It took me long time to go thru' your posts and try to understand the stuff. Much of what you have said is still way over my head but I am trying to understand as best as I can.Quote from acrary:
I'm planning on showing how to setup a research platform using excel. After that it'll be what most of you are waiting for..."How to build your first system"
I want to especially thank you for sharing your "Edge Test" concept that you have mentioned & explained many times in your other threads. That has completely changed the way I think about building & testing trading systems.
--TraderChip
acrary,
This might be a stupid question but what is the best way to generate the random trades in the edge test?
I would like to test against an intraday system that i have currently.
It seems like you're trying to do apples to apples comparisons by selecting trades of equal durations so i'm wondering if for intraday that still applies (trade duration) and if I should also consider being comparable in the sense of time of day too? (because there is more volatility at certain times of day)
Also, my system uses profit targets, would i use similar targets for exit in my random entries?
Or possibly even use an identical exit strategy?
It seems like you could "edge test" both your entry and exit separately...
these are probably questions you have already answered, if so please point me to the appropriate thread. I tried searching but i couldn't find the answer to this particular issue...
thanks
This might be a stupid question but what is the best way to generate the random trades in the edge test?
I would like to test against an intraday system that i have currently.
It seems like you're trying to do apples to apples comparisons by selecting trades of equal durations so i'm wondering if for intraday that still applies (trade duration) and if I should also consider being comparable in the sense of time of day too? (because there is more volatility at certain times of day)
Also, my system uses profit targets, would i use similar targets for exit in my random entries?
Or possibly even use an identical exit strategy?
It seems like you could "edge test" both your entry and exit separately...
these are probably questions you have already answered, if so please point me to the appropriate thread. I tried searching but i couldn't find the answer to this particular issue...
thanks
Quote from acrary:
What if you have a trading model that trades stocks in the Nasdaq? Would it be appropriate to keep that as one model? Or possibly break the stocks into their perspective sectors and have numerous sector models where you could use your correlation and weighted designs to add each sector model only if improvement is made to overall return and risk?
You could use it either way. Instead of looking for many non-correlated models/markets you could just do pairs trading based on two non-correlated models for each security, basket of securities, or market sector. If you had 10 sectors you could then give 10% to each pair and recalculate the pool every so often or you could take the results from the 10 sector pairs and run them through the weighting test to see how much each should get from the pool and allocate funds to each after every trade. [/B]
Acrary, your response is greatly appreciated.
I am having some problems understanding your meaning of pair trading two non-correlated models for each security, basket, or sector. Do you mean just matching two models up for each sector with your correlation studies or are you referring to something else entirely? I'm probably reading too much into this.
Just to give an update, I finally got around to testing my original model against the idea of breaking into various sector models. The results were encouraging. Tests were based on the following:
1) Set A: Picked several sectors that enjoyed three consecutive years of profitability.
2) Set B: Picked a matching number of sectors that did not achieve three years of profits.
3) Universal Set: combination of Set A and B to test whether breaking into sectors is valid.
Ran tests on the model for the following two years on Set A and profits/drawdown were improved from the Universal Set. Tests on Set B showed profits/drawdowns worse than Universal Set and Set A.
Ran these tests against a few different year and sector combinations and again results were encouraging.
While these tests proved useful I won't rely too much on the results since most sectors experienced annual profits and thus didn't give me enough bad sectors to test with. I'll next work on scaling down into Monthly performance figures to really begin testing this idea.
If results stay encouraging...I'll begin testing the addition of these sector models into the overall model portfolio via your correlation ideas.
Thanks again for sharing your process. Can't wait to see the research platform you mentioned.
acrary, where did you go? im sure all would like to see continuing activity in this thread.
- Status
- Not open for further replies.