Skip to main content
Quantitative Finance

You are not logged in. Your edit will be placed in a queue until it is peer reviewed.

We welcome edits that make the post easier to understand and more valuable for readers. Because community members review edits, please try to make the post substantially better than how you found it, for example, by fixing grammar or adding additional resources and hyperlinks.

Required fields*

9
  • $\begingroup$ Thank you a lot for your answer! It was really really helpful. I would like to send you the code for you the check it out, but the harsh truth is that I still don't have any. I'm still at a stage where I have a lot of concepts in mind but no idea how to actually put any of them on code. Here are some of the (very theoretica) approaches I had in mind (next message) : $\endgroup$ Commented Jul 5, 2020 at 21:00
  • $\begingroup$ 1) Creating a neural network, feeding it images of patterns i like and let it loop through charts to see if it can find the patterns I chose 2) A more mathematical approach which would involve using minima and maxima, just like you suggested 3) Find a way to convert ohlc data to a series of values that I can use to "quantify" that pattern, then I can loop through other charts and see if there are new patterns that have similar values to the one I "quantified" $\endgroup$ Commented Jul 5, 2020 at 21:03
  • $\begingroup$ @Jack022 not sure a neural net will be efficient in this, the geometric approach would have my preference (I like NNets in general: arxiv.org/abs/2006.09611 but not for this) $\endgroup$ Commented Jul 8, 2020 at 10:00
  • $\begingroup$ Yes indeed. I've been thinking about this approach and it seems the best one to go for now. My main focus and biggest trouble right now is putting it on Python code $\endgroup$ Commented Jul 8, 2020 at 11:04
  • 1
    $\begingroup$ @Jack022 I updated my answer to reflect my comments on the link you found $\endgroup$ Commented Jul 9, 2020 at 21:53