I believe that 25% is a fair rate, which is prob similar to an Optimal F output.

@Grant yeah, got similar thinking. which is why I played around those values

but that's late game. I want that snowball

----------------

looks like markets gonna struggle down further

bunch of fake optimism without an actual rebound

US debt records, Russian drama, SPY falling again

but at least that's a movement!

enough of that 1% channel sideways bullshit

stuff that I dislike:

AC
ADO
ADX
ADXR
Alligator
BOP
CCI
CMO
Coral
DPO
DX
FractalHigh
HMA
MinusDI
NumWhiteBlack
PlusDI
QLSMA
ROC
RSI
SAR
SentimentLW
SentimentG
SIROC
StochRSI
T3
UltOsc
VolatilityC
VolatilityMM
WCLPrice
WillR
WMA

Out of interest, what is strategy performance like when you backtest with WFO?

While some of the metrics you post look good, I do wonder how robust the logic actually is, and whether you are massively overfitting entry / exit criteria just to generate good number on paper.

man... where do I even start...

WFO ain't some kind of magic bullet

you do realize those numbers are over 9 months period of time, right?

to put it in perspective - January performance shows AR of 64%

yes, I am massively overfitting

that's the whole idea - THE strategy

what you call overfitting - I call strategy development

there are tricks so arcane Mr. Ehler himself would start crying

it's not "just to generate good number on paper" but gradually, over time - filter out good stuff until it starts behaving live

that's all there is - a backtest. somewhat close approximation of what would have happened in past

that is the ONLY weapon you get unless you are into moon phases or insider trading

I try to understand your thought process, but I don't.

Why would you develop a system, knowing on beforehand that it will clearly over-fit on your in-sample data?
Knowing how your system behaves on out-of-sample data should be key before going live.

because you don't consider that my in-sample data is all the meaningful data there is

my out-of-sample data is tomorrow's failure

what else you want me to test it on?

different asset? generated white noise? Mozart's 40th symphony?

----------

WFO moves the starting point and tries to find best optional parameters

I run it on full history and don't parameterize strategy apart from stuff that controls position size

(although occasionally I do slice it up and analyze particular week or month to gain insight about most conflicting parts)

With `EndDate = 20220202;`



Without `EndDate = 20220202;`



With `StartDate = 20220201`