First results SAR Strategy …

zilliq · Tue, 08 Sep 2020 12:43:00 +0000

Hi Guys, To continue on our last discussion on overfitting here are the first results on OOS The idea was to evaluate/confirm that less variable = better OOS correlation That’s why I test a very simple strategy based on SAR with only 2 variables (Signal if close crosses SAR) As always strategy = Signal (SAR) + Analyse of the market structure + Money management Backtest wasn’t famous with only 58,99 % winners on 556 trades ! 100 000 units EUR/USD 1 mn Sharpe Ratio 1.1. There was the backtest of this week-end As you see on 100 000 units the equity curve wasn’t really linear (As usual with only few variables)

This topic has 57 replies, 10 voices, and was last updated 4 years ago by zilliq.

Viewing 15 posts - 16 through 30 (of 58 total)

← 1 2 3 4 →

09/09/2020 at 1:40 PM #143744

zilliq

zilliq wrote:

Stupid strategy like this one based on Stochastic (3 variables, one for signal, one for market structure, one for Money management)

// / Signal ///////<br /> indicator1 = Stochastic[4*a,a](close)</p> <p>c1 = (indicator1 CROSSES over average[5](indicator1))<br /> c2 = (indicator1 CROSSES over average[5](indicator1))

1

2

3

4

5

// / Signal ///////

indicator1 = Stochastic[4*a,a](close)

c1 = (indicator1 CROSSES over average[5](indicator1))

c2 = (indicator1 CROSSES over average[5](indicator1))

With this kind of backtest

End of day for this stupid Stochastic strategy too . Goal reach on OOS

+ 21 % but 80 % in Market = bad strategy saved by stats

zilliq
Participant

Topics: 58
Replies: 683
Been thanked: 152 times

09/09/2020 at 5:12 PM #143778

bertrandpinoy

aller met sur sur vinted! on te fera une belle offre LOL

bertrandpinoy
Participant

Topics: 25
Replies: 125
Been thanked: 8 times

09/09/2020 at 5:24 PM #143780

zilliq

Only in english Bertrand, some will be angry 😉

Not sure for Vinted 🙂

1 user thanked author for this post.

Vonasi

zilliq
Participant

Topics: 58
Replies: 683
Been thanked: 152 times

09/09/2020 at 5:48 PM #143783

Scooby

Market will be open soon 😉

Scooby
Participant

Topics: 9
Replies: 52
Been thanked: 26 times

09/10/2020 at 10:00 AM #143836

zilliq

OOS Today : Algo stop for the Stupid algo on Stochastics +32 % in 3 days, Stupid Algo on SAR can continue to take trade today + 42 % in 5 days

Not bad for 3 Bad Donkeys 🙂

zilliq
Participant

Topics: 58
Replies: 683
Been thanked: 152 times

09/10/2020 at 6:02 PM #143890

zilliq

End of day for Bad Donkey SAR +52 % in 5 days, not too bad Sharpe Ratio 2.61 not bad

Very intersting it takes only short, and now only call

We will see tomorrow (The system stop this afternoon because of Goal reach)

See U

zilliq
Participant

Topics: 58
Replies: 683
Been thanked: 152 times

09/11/2020 at 12:26 PM #143945

zilliq

Complicated today because of long range period on EUR/USD (Friday…)…Less opportunities for Donkeys

We will see at the end of the day what they did

zilliq
Participant

Topics: 58
Replies: 683
Been thanked: 152 times

09/12/2020 at 12:51 AM #143988

danistuta

For curiosity which indicators do you use in your strategy for EUR/USD? Thank you.

danistuta
Participant

Topics: 31
Replies: 70
Been thanked: 2 times

09/12/2020 at 10:15 AM #144008

zilliq

@danistuta

SAR as indicated in the title

As I thought, the algo don’t take a lot of trades yesterday and doesn’t reach our goal (1000 USD/day)

+62 % in 6 days, not very bad for a bad Donkey SAR

And the bad Donkey based on STOCH as not taken any trade yesterday and finish at +36 % at the end of the week (3 days)

We will see next week

I let the Algos run (I don’t do another backtest to recalibrate the variables) to see what happen and when they will lose a lot

Bye

zilliq
Participant

Topics: 58
Replies: 683
Been thanked: 152 times

09/12/2020 at 10:17 AM #144011

danistuta

Only Sar indicator? And which timeframe do you use?

danistuta
Participant

Topics: 31
Replies: 70
Been thanked: 2 times

09/12/2020 at 10:23 AM #144012

zilliq

The purpose is to determine when we need to recalibrate the variables (One week, 2 weeks and so on ..) too. I have my idea but noone knows

But sometimes it can be long to know as on this algo with OOS since mid august. We know one day it will fail (And should recalibrate) and we just need to wait

Have a nice week-end

zilliq
Participant

Topics: 58
Replies: 683
Been thanked: 152 times

09/12/2020 at 10:40 AM #144015

snucke

is this how you build your algos that you use on real accounts?

snucke
Participant

Topics: 9
Replies: 143
Been thanked: 21 times

09/12/2020 at 3:09 PM #144031

zilliq

@snuckle

These algos are not on real account, not yet, this is demo OOS (For confirming/correlating with backtest on IS), because I’m waiting for the PRT v11 on IG (For 2D/3D optimization , other options …) and do a lot a lot of test, hypothesis, simplyfying codes, trials (I code may be 10 years on PRT, or more, I don’t remember)

I create like these all algos, put them on “incubator”, wait if they work or not (a lot of trials go directly in trash) and if so will put them on IG V11 when available (I’m waiting desperately like others options on PRT (Backtest on indicators …))

Bye

zilliq
Participant

Topics: 58
Replies: 683
Been thanked: 152 times

09/13/2020 at 9:12 AM #144050

zilliq

@danistuta

1 mn as indicated on first page

zilliq
Participant

Topics: 58
Replies: 683
Been thanked: 152 times

09/14/2020 at 6:50 PM #144247

zilliq

Bad SAR Donkey works well today

+/- 10 % today, +71.85 % since 7 days, 14.35 % in the market = very good

Bad Stochastic Donkey works bad. After a flat friday, -1 % today, +35 % since 5 days, 44.54 % in the market=bad for me

We will see tomorrow

zilliq
Participant

Topics: 58
Replies: 683
Been thanked: 152 times
Author

Posts

Viewing 15 posts - 16 through 30 (of 58 total)

← 1 2 3 4 →

Find exclusive trading pro-tools on

First results SAR Strategy …

1 user thanked author for this post.