Search results

Watch an Advanced Algorithms class on YouTube. For example: Sometimes, I'm out in seconds. The sound of chalk on blackboard is a sleep inducer, so thanks Jalani Nelson! Regards, PTR

Shit, prison was the best thing that ever happened to me. Everyone should go. First day out I got a 99-cent cup of McDonald's coffee and thought boy, freedom is fabulous. Gratitude and thanks every day, didn't think life could be this sweet. Regards, PTR

Go to the cafeteria of a major car manufacturer, and you'll find 9 out of 10 "engineers" from India, especially TCS (They Copy Software). As you say, it's a culture of agreeable liars and passive-aggressive backstabbers. But what's even worse is the American executives who hire these offshore...

The end of 1999 was the meltup of all meltups. You could buy any tech IPO and watch it go 10X within months. QCOM, COMS, BRCM, just to name a few. Funds up a few percentage points in July of that year ended up +100% by December 31st. It was a ridiculous, fun, and a fish-in-the-barrel experience...

iexcloud.io https://github.com/ScottfreeLLC/AlphaPy

And the worst programmers in the world, especially TCS (They Copy Software). Regards, PTR

Right, validation AUC is 0.67, and the probabilities are well-calibrated, so we can apply a filter to trade the correct system.

I'm using AlphaPy and XGBoost to predict the next day's range. It's a simple classifier to predict the probability of the next day's trading range to be above or below its ATR. My question is: What do you consider to be the simplest intraday trend and counter-trend systems? I'm considering ORB...

Depends on the application. I write PySpark pipelines for big data all the time and deploy models in 50 lines of code or less. You don't have to write much code for model deployment any more, as much of the work has been subsumed by high-level ML APIs or products such as DataRobot...

We can expect a lot more of this: https://www.bloomberg.com/news/articles/2019-05-06/who-to-sue-when-a-robot-loses-your-fortune

Most of these answers are crap. Either use the multiprocessing package (groupby vectorization for multiple cores) or Dask.

Check out AlphaPy here: https://github.com/ScottfreeLLC/AlphaPy The key for trading is to use the probabilities generated by your classifier as trading signals. The higher the probability, the higher the confidence in the signal. For neural networks, I would focus on trading regimes (e.g...

Refer to acrary's thread.

Yeah, anyone can do TEDx, even convicted pedophiles.

https://github.com/ScottfreeLLC/AlphaPy https://www.quantopian.com

As a software engineer in my 20's back in the 80's, I had my own office and we used to fly first-class everywhere. Today, you'll most likely be stuck in an open office plan with a bunch of smelly Indians who steal your code. Regards, PTR

I like where the IEX is going: https://iexcloud.io/docs/api/

Man, you really have to wade through the BS to see any real answers. Here are two options for you: Pay for IBD (investors.com) Write your own screener (quantopian.com)

It is amazing how few people end up doing time, except for me and my billionaire friend.

I'm working on this one in Python... https://github.com/ScottfreeLLC/AlphaPy It uses machine learning and shit...