A share to challenge your alcohol-soaked brains😄
I've been doing some more ML stuff. Deeper! Trying to get it all native C#
Anyway - A useful test this, in itself. I gave a model 600 days of 1m data and asked it to model if the price would be +/- 10 pts in 15 bars time... More importantly, I gave it a bunch of commodity indicator outputs using the defaults (as any 1m chart scalper would likely do!). I dug into the model to find which columns it found most useful as predictors. This may be a new benchmark test for me!

Figured out how to save and restore model data (arrays mainly) efficiently. So, now, I can share and distribute trained models!
Beer really does work... Trained for 80 range and hooked in with profileBars. 90 days of training data on the 7-day chart. Awesome companion! (zones are from HeikenAshi indie)

Work in progress
KNN ML - Stores all the patterns of past bars, then iterates over all those patterns finding the closest X matches to now, and from those matches, calculates the probability of what happens next. Simple ML, but quite well suited to this, I think You do have to believe, however, that past history is in fact reflective of what might happen in the future...

Was reading some articles on the MQL site yesterday and it got me to thinking.. (btw - even though I do not use the platform, MQL has articles and user contributions the other platforms like Ninjatrader can only dream about!)
So, some research starts Anyway. Looking at short term trend probabilities over a set number of brick style bars (12 range in this case). This histogram represents the imbalance of up or down closes in that range. I am just going to let that sit for a while, and marinate... 🍸

Very narrow range. Magnet below. Singles need fixing. If breaks with some follow-through, it's the logical spot (but when has NQ ever been logical!?). Singles are all filled. Took some off at the end. Some magnets are about 10-20pts lower, but...

Came up with a completely new way to score chart /indicator patterns yesterday. Just finished coding it. Works on reversal-type bars. The idea is, you take your pattern, then add or subtract the Abs(Open-Close) of the next bar. This gives you a little score on continuation bars ..and a big score on reversal bars (because, of the reversal-type chart). Iterate through all your bars and each pattern ends up with a sum of the scores. Some patterns will be wildly positive, some negative. You're in the middle is chop. Auto-biased for the current action.

#Nasdaq Levels share (I added a legend!) Clear as mud. I am out today, so hope you just keep on playing tennis until I get back...

I try all sorts of whacky stuff on weekends. Most of it ends up being totally useless. I waste far too much of my life on this stuff!
Currently backtesting over the last 2 weeks with my day-to-day trend algos. Decided to break my order into parts and spread it over 100 nq pts 1/ Result? A mediocre profit turned into a much larger profit 🤔
The same risk control and stop were used. Only the initial entry size was much reduced. A much higher profit was attained. A sizeable one-way drive over 100pts would probably hurt 2/

Hmmmm. I think it's code a crazy indicator time... Bar retests - Every scalper should know these stats!?

Having fun yet!? Bloody chop Was OR 5m mid, btw

Mkt slow - Made coffee money, so just doing research.
An idea share (just been working on it). Physcology-based trades (the best!)
Take fav oscillator (this is StochRSI / 60m chart).
Mark Ray on bar H/L when entering extremes (where mean traders start counter-trading). 1/ Realise how often they get killed (at least in the short term). This should be a lesson for you in itself!
Realise how often price retests those levels for a bounce.
Makes sense, no? They get out when they are in back profit. Orange lines are examples. Try it. Let me know... 2/

Back at home and reading some DM's (long thread warning!)
I'd like to make it clear - I do not have a magic strategy to sell/offer/give. I cannot 'tell' you how to be profitable. I can share some stuff I do on here, and you can use it how you see fit 1/ I can share some of the tools I use/built, that I could not make money without (and I do!).
I can share levels and ideas (I do!).
But _you_ have to turn that into something you can execute because it is different for us all.
I have spent many years staring at screens. 2/

Went out and left NT8 to process the month-to-date date (replay). Takes a bunch of hours! Retrained 1st network and get this now. Red/Green is NN bias. It seems >70% accurate predicting a 10pt move within the next 8 bars forward. A few couple pages from the chart. Interesting... I find it interesting how it waits a bit, like many traders, and does not take the first pullback...

Deep Neural net in native C# running inside of NT8. Hallelujah!
I may have just worked 20 hours straight to get this working with all my inputs, but I hope if this works, I can migrate the code into other indies, too! So, what's the point of this? A tremendous amount of work etc. Apart from getting rid of a bee in my bonnet, so to speak, it gives on-the-fly probabilities. For instance - The probability of a close 10pt higher in the next 2 bars, is X%, and it will do it in real-time

Morning all. NQ Do it!

Just thinking out loud. If you have a retail-type rules-based system. Even a very 'strict' rules-based system, does not mean (in all likelihood) you can apply it everywhere and still make money. I think there will always be a human discretionary component. That 'feeling'. 1/ If that were not the case, then why not just automate the ruleset, increase size, sit back and enjoy? Reason? Most people can't fully describe the process(rules) in a way that can be coded (and thus mechanically applied). I think having some rules you never break, especially 2/

Doubled day (more), shorting those highs. Just came back and saw them before. Needless to say, rather risky, but I think they were somewhat extended, to say the least! Major level. Way over range. Got some signals from algos, etc. Still have a runner after algo, just for Fri Fun Platform froze for a minute there! You should have seen me run downstairs to get my phone! PANIC STATIONS! 😆

Wanted a way to easily visualise the MFE (max favourable excursion), entry & exit on the chart from various signals to aid research. After a little thinking, triangles I thought would be nice (entry, exit, MFE).

So, here we have MFE in pts from BIAS changes in indie. Here's another one. I like looking at MFE like this. Gives me a better idea of what you can actually shoot for and helps me avoid bailing early. Not sure many people optimise on MFE. It makes sense to me (at the moment!)

If your fingers are not too cold to click, I am looking at this for an opening play. Just a guess.

Also, I am going into Christmas semi-hibernation! Smaller size, not so much trading. Volume will be likely falling and I will just do some small scalps until the new year now. Will probably spend the time researching stuff, trying to get presents for family, etc. So, if you have any interesting ideas ;)

I came up with a new scalping strategy today.

I will share it here, in case anyone wants to review it. It really is extremely simple, but I think with discipline, it can probably be executed profitably (I am hoping so - I will find out this week) So, NQ (though may work with others, especially DAX), but you need a reversal type bar for reasons I will explain. I am using 34 ticks here (not optimised - It's just what I use).

Here is a clean example chart. The bars of interest are marked with the coloured diamonds here

Perfect walking weather... This ring dates from 1530.