collapse

Author Topic: Walkforward Analysist , Walkbackward Analysist, Curvefitting : To Gain Robbust  (Read 299 times)

Online bismillahwd

  • PAMM and SIGNAL
  • Sr. Member
  • ****
  • Posts: 597
  • Private Trader Still - Hedge Fund Soon
    • https://ordequity.signalstart.com/
in 2014 i do WFA,

tons of learning also in asirikuy about how robust is WFA method, trade on open bar only, etc2

but its an effort too much, i always WFA my EA for weeks or month. And an Open Bar EA surely had long stagnant Drawdown period.



As at the end , im coming to my own conclusion, continous WFA is also curve fitting it self. In a different way.

I even see another silly method "WALKBACKWARD analysist" LMAO Hahahahah.



Hey, i mean it in esential way,

If we curve fit the last period, and we test the ea in the oldest period as out of sampling, it also an OUT OF SAMPLING METHOD

Even lanchester the developer of Multiple ea do that. Optimized for last 6 month, but make sure the results in the early year also profitable.

In early years period means = OUT OF SAMPLE.

No mater what we trade in the past or future, esentially it still OOS for testing robustness



In WFA The Best Out of sample we pick, is the best that we choose to live trade.

So whats different than curve fitting??

The results in Live trade, the market always change beyond our expectation.

Even with continous development.

The last market behaviour is the least we could adapt with our optimization.



Even i know a friend works in a real Financial Institution, a 20 years trading experience in a hedge fund.

From what i see, the way he do to adapt market change is no different than curve fitting.



Im not saying WFA is a wrong method, i also still had WFA tools, but rarely using it now.



So, as a simple statistic approach, why dont we build a most robust system that all in sample data we could had?

Even it tooks hundreds hour for a single curency. (With TickData also now!)

The more sample we optimized is the more statisticly robust proven. No matter what the market behavior change, historicly some of it repeated itself.

Market Trade only know 4 behaviour : Trend, Reversal, Breakout, and Ranging. Only the volume volatility that changing.

Then i optimized all the historical data as robust at we can with as much data as i had.

And build porftolio with those 4 character inside to minimize stagnant period. And took every chance in every condition change.



Then picking up the best KPI from it optimization results.

Such as Profit factor, CAGR, etc. But Not get too shiny on the score itself, since those Profit Factor, CAGR, Payoff, etc always had flaws statisticly

So i pick with the most trades as posible first, that mean the more data, more sample and most market condition as we could had.

Run montecarlo, stagnancy period, drawdown % and period analysis with the risk that we could stomach.

And dont change the rules and system before that max risk happened. Wich mean market still in our portfolio prediction.

(So actually i do WFA also now, but my out of sample is a live trade. LOL. Kidding)



However this is my personal conclusion. Dont pick it if you dont walk the path yourself.



Im not bashing out Asirikuy with WFA approach, but i felt like im wasting times backthen sticking to others personal rules to build a systems.

But however, he build a great platform and different insight.



No matter what system we build, tick scalping, swing, to long trend trading, or even a Grid.

Whatever approach we choose,  Even now im doing curve fitting to "latest market condition" approach. From the base parameters that already robust entire period as much i can have. And back using TDS Variable spreads ON.

As It IS the "TRUE real market condition". Not open bar.



At the end of the day, we trade to made money.

Not to be a smart academicly.



So for me the hints is as i mention above "Run the system with the max risk we could stomach with".

No matter we use WFA or Curve fitting the whole period method.

Managing Risk first, then profits follow.





Cheers,

My two cents





Once again : this is my personal conclusion. Dont pick it if you dont walk the path yourself.







PAMM :
https://www.alpari.org/strategy/ORD-Equity
https://alpari.finance/ru/invest/pamm/491907/#pamm-return

SIGNAL :
https://ordequity.signalstart.com/
https://ordequity.signalstart.com/analysis/ordequity3xrisk/207352

https://www.zulutrade.com/trader/128850

https://www.mql5.com/en/signals/975270?source=Site+Signals+My

https://www.mql5.com/en/signals/989449?source=Site+Signals+My


IMPORTANT UPDATE

updated announcement for signal copier :
i put info too in Signal Start Info :


"Hope u are using the most similar broker to get price feeds as master copier

note : Alpari RU and Alpari INT are similar feeds, Peppertsone and ICmarkets is good also, Maybe Tickmill too.

Just check slippage and ping times in Slippage Tab in here (upsthere)
Alpari Int (Risk Moderate)
https://www.mql5.com/en/signals/975270?source=Site+Signals+Page#!tab=slippage


But this one is better :
Alpari RU (Risk 3 Times)
https://www.mql5.com/en/signals/989449?source=Site+Signals+My#!tab=slippage"

Online diyforexskills

  • Verified Vendor
  • Hero Member
  • ***
  • Posts: 2240
I agree with much of what you write; in whatever way we do optimisation, we are "curve fitting".

My few observations on this from the past 10 years.

1. Even optimising over 19 years (all sorts of market conditions) as I once did for some 10 currencies, still results in failure. Six to 12 months is more than enough. The more important thing is to actually look at the charts to see what the market was like over the period you choose to optimise. Then you can make an informed decision as to whether you should re-optimise if things go bad. eg if by chance you had optimised over what was largely a trending period with low ATR, and now the market is ranging with high ATR, then yes, re-optimisation is called for.

2. Over trading is the biggest sin. Yet we are often encouraged to choose optimisation runs with at least 100 trades for statistical reasons. These days I am far more relaxed about choosing optimization runs with around only 40 trades (and very high PF) or even less based on what I see on the chart; provided that they occur at times that I would have placed such trades had I been trading manually (yes we need to do a Visual BT of the optimisation run we choose to see if the trade entries make sense). And yes, we will miss having the EA place trades that would have won, but the low numbers mean tight entry conditions, and tight entry conditions mean that we are likely to lose less often going forward.

3. These days I always optimise separate strategies for Buys and Sells. The optimum parameter settings for going long or short are always different in my experience.

4. Yes, risk first, then profits. Which also means placing as much emphasis on the exit conditions of a strategy as on the entry conditions; I always use a dynamic, parameter-based exit as well as the pip-based TP and SL settings.

My two cents worth.  :)

Online bismillahwd

  • PAMM and SIGNAL
  • Sr. Member
  • ****
  • Posts: 597
  • Private Trader Still - Hedge Fund Soon
    • https://ordequity.signalstart.com/
I agree with much of what you write; in whatever way we do optimisation, we are "curve fitting".

My few observations on this from the past 10 years.

1. Even optimising over 19 years (all sorts of market conditions) as I once did for some 10 currencies, still results in failure. Six to 12 months is more than enough. The more important thing is to actually look at the charts to see what the market was like over the period you choose to optimise. Then you can make an informed decision as to whether you should re-optimise if things go bad. eg if by chance you had optimised over what was largely a trending period with low ATR, and now the market is ranging with high ATR, then yes, re-optimisation is called for.

2. Over trading is the biggest sin. Yet we are often encouraged to choose optimisation runs with at least 100 trades for statistical reasons. These days I am far more relaxed about choosing optimization runs with around only 40 trades (and very high PF) or even less based on what I see on the chart; provided that they occur at times that I would have placed such trades had I been trading manually (yes we need to do a Visual BT of the optimisation run we choose to see if the trade entries make sense). And yes, we will miss having the EA place trades that would have won, but the low numbers mean tight entry conditions, and tight entry conditions mean that we are likely to lose less often going forward.

3. These days I always optimise separate strategies for Buys and Sells. The optimum parameter settings for going long or short are always different in my experience.

4. Yes, risk first, then profits. Which also means placing as much emphasis on the exit conditions of a strategy as on the entry conditions; I always use a dynamic, parameter-based exit as well as the pip-based TP and SL settings.

My two cents worth.  :)

Mann, Absolutely!!!
I cant add more about your conclussion  ;D


Agree, When market volatily change, then RE OPTIMZED is should be done.
For me also There aint no such a things as Robust test by WFA, for long lasting free works with automated trading.
We just curve it em with in other way.

You did for several month opti, yes i did to, a years max,
PF 2 is the lowest i can accept,
Even my most strategy almost run with 3-4 PF, maybe 1 trade only in a weeks,
but with 12 pairs, we had it covered a week full of trading day.

About one buy one sell different opti, im agree too.
Its fundamental approach that we put in technical,
IE when the bank said X rate for the curency, the pair behaviors would had tendencies for trending before the a certain amount of month,
so the volume of buy and sell would be different.

About the builder software now im only focus on portfolio analyzer, or any of it. SQ and Porto Architect had it. Just to make sure the diversification is correct, for subtitute the loss that a pairs had.
I alway had under 0.3 corelation to run with.
Thus the equity curve is going smoother with low stagnant drawdown days.

WFA? i had it, but dont use it no more :D




Gosh, thanks bro.

U just made my day, i tough im alone in here






PAMM :
https://www.alpari.org/strategy/ORD-Equity
https://alpari.finance/ru/invest/pamm/491907/#pamm-return

SIGNAL :
https://ordequity.signalstart.com/
https://ordequity.signalstart.com/analysis/ordequity3xrisk/207352

https://www.zulutrade.com/trader/128850

https://www.mql5.com/en/signals/975270?source=Site+Signals+My

https://www.mql5.com/en/signals/989449?source=Site+Signals+My


IMPORTANT UPDATE

updated announcement for signal copier :
i put info too in Signal Start Info :


"Hope u are using the most similar broker to get price feeds as master copier

note : Alpari RU and Alpari INT are similar feeds, Peppertsone and ICmarkets is good also, Maybe Tickmill too.

Just check slippage and ping times in Slippage Tab in here (upsthere)
Alpari Int (Risk Moderate)
https://www.mql5.com/en/signals/975270?source=Site+Signals+Page#!tab=slippage


But this one is better :
Alpari RU (Risk 3 Times)
https://www.mql5.com/en/signals/989449?source=Site+Signals+My#!tab=slippage"

Online bismillahwd

  • PAMM and SIGNAL
  • Sr. Member
  • ****
  • Posts: 597
  • Private Trader Still - Hedge Fund Soon
    • https://ordequity.signalstart.com/


forgot to add one :
The Exit Strategy is 75% more important than the entrance.


And then from our conclusion here,

There is no such a things as free "automated whole living work free" trading system.
No matter what school or course its, the market will kill for whatever said as robustness
wheter its trade on open bar, or tick scalping, or even grid.
At the end of the day, we trade to MAKE MONEY, not to be smart, even i saw a trader that trade for living that didnt even pass grade school LOL

I really dont buy, the concept of open bar trading system, anti scalping, anti grid bla bla bla that called as Robust.
As i know much PAMM out there that ran great for years period, they even do grid, and scalping.


So, for me
EA is only a tools to open and close the trade for our trading system,
We gotta work our ass to opti and re opti the system periodictly as the fundamental change, to keep up with the market.


Anw, great discussion mate, respect









PAMM :
https://www.alpari.org/strategy/ORD-Equity
https://alpari.finance/ru/invest/pamm/491907/#pamm-return

SIGNAL :
https://ordequity.signalstart.com/
https://ordequity.signalstart.com/analysis/ordequity3xrisk/207352

https://www.zulutrade.com/trader/128850

https://www.mql5.com/en/signals/975270?source=Site+Signals+My

https://www.mql5.com/en/signals/989449?source=Site+Signals+My


IMPORTANT UPDATE

updated announcement for signal copier :
i put info too in Signal Start Info :


"Hope u are using the most similar broker to get price feeds as master copier

note : Alpari RU and Alpari INT are similar feeds, Peppertsone and ICmarkets is good also, Maybe Tickmill too.

Just check slippage and ping times in Slippage Tab in here (upsthere)
Alpari Int (Risk Moderate)
https://www.mql5.com/en/signals/975270?source=Site+Signals+Page#!tab=slippage


But this one is better :
Alpari RU (Risk 3 Times)
https://www.mql5.com/en/signals/989449?source=Site+Signals+My#!tab=slippage"

 

browse forum