My experience has actually been okay with medium. Totally acknowledge that signal to noise is abysmal but sometimes it’s better to get something kinda right in broken English as a push in the right direction than to be completely stuck.
...and how 'bout a "And Good on 'im!" Jeez, guys -- how 'bout being happy for someone showing some umph? My "Current Projects" list is about 6 months olde.
Though I would say that being positive and encouraging while maintaining high standards is the best of all things. My problem is that I'm a total jerk. I so often have to sit and just think about the ways I'm a jerk and then try to imagine being different. The only solution I can find is to go find people who are bigger jerks than me.
Thanks for the suggestion of the caret package. In this strategy here, I only focus on predicting the next day's price direction and not the asset price itself. In other words whether the candle will be bullish or bearish, and then take an entry consequently.
As a "total jerk", you're a real piker, Noobs. A Noob to the tenth degree. ("Boy! You sure tol' him!" Yeah I did. Ye-ah. )
On a side note, anyone ever saw a relevant Medium.com trading article? If so, feel free to link. I recently became a subscriber for reading casual astrophysics and AI articles but I might as well read any relevant trade related stuff, if there is any. The only articles I saw this before basically were "using standard ML classifier to calculate bunch of irrelevant stats on stock price series, probably in-sample" or "mean reversion strategy that only is long in ES and has Sharpe 0.6 before transaction overhead". That said, I didn't try to look very hard beyond my daily recommended digest.
Thank you for sharing. May I ask you a couple of questions: 1. This: is just a set of "rules"? 2. This: is the learning algorithm? It is just Bayesian statistics. So you apply a probability to the parameters you use? This is no different from say using Kalman filter algorithm, I don't see any "learning" involved. 3. Any bias/drift of the data set will produce a non 50/50 outcome? 4. In my simplistic view, learning means I change the parameters when I find them not useful, not by adding noise term to the parameters? Not sure if I make any sense, if not, just ignore my questions. Thank you.