Pattern matching price movements in PRT – machine learning

Wing · Fri, 03 Feb 2017 16:45:14 +0000

I am wondering if anyone out there has experimented with pattern matching, in PRT, or using another platform/language. By pattern matching, I mean for example: comparing the last 20 bars, trying to find a sequence of 20 bars in previous history that best match it. From this you can make predictions on how such a similar event will fall out. You compare two price sequences by finding a common low and/or high point as your base(s), and then compare each close. The difference between each close is then squared and a total score is produced for the sequence. The sequence with lowest score is the best match. Advanced algorithms would compare highs and lows as well. Now, the problem is that PRT has a limitation on the number of iterations (for loops/if statements) that you can include in a system. This is probably to reduce server load. It also counts all indicators used in a system, so the max iterations are applied to the whole system. I believe this limit is 150 iterations per bar or something. It is possible to check for example this day’s price movement from 9;00 to 11:00 as compared to the same time period for each of the previous 100 days or so. To me, this is not enough. I have tried this out, but I am still unsure whether pattern matching is a viable strategy. In what markets/timeframes do you know/believe it performs well, or at all? To battle this limit on PRT iterations, I have a few ideas in mind: Create multiple systems/indicators, that each check a certain time period every day. Build a smarter pattern matching algorithm that relies on high/low points instead of brute-forcing and checking every bar in every sequence. Does anyone have any ideas on this? If I can only compare a 15-bar sequence to 100 other 15-bar sequences, then create a filter that only compares it to good sequences. For example: sequence has a minimum range or is in a down/up trend. Reducing the number of iterations by storing/checking information in variables in a better way. Why, oh why, are there no arrays (except indicator arrays) in probuilder/proorder? If the above fails (which may be likely), build this pattern matching algorithm in another language. Would appreciate any ideas on how to accomplish this. Ready to explain my ideas further if there are questions. I might post some code soon of my experiments so far. I will also add that a bar sequence can be compared in two ways: with or without relativity. To compare two price movements that look similar, but where one has a range of 100 points and the other 50 points, the large one will be compressed to more easily be compared with the smaller one.

This topic has 18 replies, 1 voice, and was last updated 2 years ago by Khaled.

Viewing 4 posts - 16 through 19 (of 19 total)

← 1 2

05/17/2017 at 3:55 PM #35855

JC_Bywan

A very interesting topic, I would love to have arrays, multitimeframe, bigger loop capacity (the “infinite loop” error message arrives way too soon even when the loop is limited), ability to store patterns with a save function not to recalculate them at each session, and ability to draw in the future in order to project predictions from machine learning on pattern recognition and monitor reality against the baseline of the prediction, all within PRT… Prt dev team, if you read us, yes we’ve been told multitimeframe arrives soon, and thanks for that, but we’d love to have all the rest too in future versions to do this, thanks 🙂

4 users thanked author for this post.

Bel, Francesco78, Maz, Nicolas

JC_Bywan
Moderator

Topics: 20
Replies: 2657
Been thanked: 925 times

05/17/2017 at 4:12 PM #35860

StantonR

Awesom thread cant believed I missed it.

StantonR
Participant

Topics: 7
Replies: 70
Been thanked: 7 times

10/26/2017 at 12:02 PM #50599

Leo

Nice Topic! I am not use to the idea of machine learning but I will think a lot about it

About the first part of you code, can you please explain me how or why you define the variable “best” in this way and not another?

When I was reading the first post of this Forum “Build a smarter pattern matching algorithm that relies on high/low points instead of brute-forcing and checking every bar in every sequence. Does anyone have any ideas on this?”, something come to my mind:

What if instead of bars we study the movement of a Hull Moving Average everytime it changes the slope direction and we store the barindex and the level of the curve, so when we study the past we try to predict how will be the next direction change…

Leo
Participant

Topics: 17
Replies: 357
Been thanked: 144 times

01/02/2022 at 1:50 PM #184326

Khaled

Hey Wing,

Happy New Year!

I know it’s been a while since you posted this. Any update of your code that you can share with us?

Many thanks.

Khaled
Participant

Topics: 59
Replies: 314
Been thanked: 65 times
Author

Posts

Viewing 4 posts - 16 through 19 (of 19 total)

← 1 2

Find exclusive trading pro-tools on

Pattern matching price movements in PRT – machine learning

4 users thanked author for this post.