Technique help to reduce over-fitting

Dow Jones · Thu, 27 Aug 2020 05:00:04 +0000

Hi everyone, Today, there is a few tools/technique to avoid over-fitting, namely probacktest walk forward analysis with OOS, avoid too much variables (subjective, right?), monte carlo, robustness tester by Vonasi, avoid trade in low time frame (subjective also, right?) and etc… I like to see if there is other techniques to help avoid over-fitting, here I’m sharing 2 more that I use occasionally: 1. Optimize variables together with possibility to trade on different bar, example as below IF timeok AND Not OnMarket AND close > open AND C1 AND (oddtest = 1 or barindex mod oddtest > 0) THEN C1 can be for example C1 = close > Average[Period], then you optimize oddtest and Period. oddtest with range 2 to 10, step 2, but can be increased according to the need Period range and step depending which way to analyze the optimization: a) No. of combination exceeding 100: the top result will be selected and the more occurrence of a Period value at the top can means higher chance when trade opened at different combination of barindex, it is more resilient. PS: Con is PRT always arrange result to highest gain%, but we know highest gain% not always means a better strategy b) No. of combination not exceeding 100: exact the optimization table to excel, sort the average gain and win rate, then rate them accordingly (depends which that you like) Note: PRT optimization windows is limited up to 100 combinations. Con of this technique is limited no. of variables can be studied at a time, basically use it when you have dilemma to choose which value for a certain variable 2. Design variables to conflict each other when optimizing it too overfit, example as below SLpoint = SL * 0.01 * close startBreakeven = MIN(atrH1, 75) startBreakeven = MAX(startBreakeven, 50) trailingATR = MIN(atrH1, SLpoint) trailingATR = MAX(trailingATR, startBreakeven) SET STOP %LOSS SL As you know, higher stop loss can contribute to high win rate. Above code is having, SL (stop loss) as % of asset value, higher can contribute higher win rate trailingATR = points gained for trailing start, lower can contribute to higher win rate In this case, if you optimize SL to be as high as possible to gain higher win rate (indirectly total gain too), then it can impact trailingATR which also contribute to win rate. So the optimization has to balance by itself for highest gain. Maybe you have other technique that you used during optimization to reduce over-fitting to share?

This topic has 63 replies, 12 voices, and was last updated 3 years ago by Paul.

Tagged: overfit, overfitting, robustness

Viewing 4 posts - 61 through 64 (of 64 total)

← 1 2 3 4 5

01/04/2021 at 12:22 AM #156134

Monobrow

Ah ha, yes, good call, ill try that, 👍

Monobrow
Participant

Topics: 15
Replies: 157
Been thanked: 23 times

01/04/2021 at 4:09 PM #156282

Dow Jones

Paul wrote:

maybe if a strategy has a simple fixed stoploss & profittarget (1:1?) , you could test each signal simultaneously (and cumulative) with help of arrays in v11. Now if you have a high winratio, then it’s a true high winratio.

@Paul, yeah, but I’m not sure how or maybe not consider worth to spend with such limitation. If someone has done it, I’m happy to learn 🙂

Dow Jones
Participant

Topics: 10
Replies: 135
Been thanked: 75 times

01/04/2021 at 4:22 PM #156290

Dow Jones

Monobrow wrote:

is there a reason why you chose 21? and not 25 for Random (or higher)

Honestly, I was trying before and forget to maximize it 🙂

Monobrow wrote:

I think the results were pretty good

For me, I’ll be happy with this good start, I would supplement with QTY 2-10 too, it shouldn’t being dropping to halve of the score…myself I actually run several combinations. Like Vonasi said, I guess we can only comment from surface, it is more important for you to know the strategy and apply accordingly the VRT concept. Then put it on demo and monitor if result is consistent.

1 user thanked author for this post.

Monobrow

Dow Jones
Participant

Topics: 10
Replies: 135
Been thanked: 75 times

01/04/2021 at 5:14 PM #156308

Paul

@Dow Jones Somehow I was under the impression that set commands didn’t do the job I was after but I was wrong and the concept failed in a quick test unfortunately.

Paul
Participant

Topics: 40
Replies: 812
Been thanked: 660 times
Author

Posts

Viewing 4 posts - 61 through 64 (of 64 total)

← 1 2 3 4 5

Find exclusive trading pro-tools on

Technique help to reduce over-fitting

1 user thanked author for this post.