Using Machine Learning for discretionary trading

[mltrader77]

Good topic here. I tried to build ML model using TensorFlow (Python) and Golang to generate CSV input data. I used historical data and calculated RSI, MACD, SMA, EMA, and BUY/SELL/HOLD signals for each data point like this:

and other technical indicators (over 25 in total). I trained a model for each ticker (though I don't have much data) and run forward testing, so not too bad actually (look into screenshot)....

and then pass to model current data with all tech indicators(RSI etc... as said before), and it basically predicts buy/sell/hold...

So not sure what is the good avg gain for short trades? not perfect to be honest but I can play with other indicators and feed probably more data (kind of limited now).

 

[murray t turtle]

Let’s say my strategy gives me a short sell signal based on the pattern, but I decide not to take it. As reasoning, I give something like below:

Time of day is past 11:30, we are in Santa Clause rally mode, above 50 and 200DMA, bad news are being discounted and other stocks in the industry are trading near all time highs. VIX is at the lows. Shorts haven’t been able to gain momentum all week. Decided to skip this trade as low probability of success.

Can AI learn anything if I have thousands of such ramblings or do I need to quantify each point- like what exactly is “low” VIX, how do you define “Santa rally?” Etc?

%%
YES;
Stock Traders Almanac defines it reasonably well.
But so much of that stuff in there changes
Discretion helps, AI or machine learning never would have been done without discretion.

 

[mbquant]

Let's assume you are a consistently profitable discretionary trader (or have full access to his/her trades and, most importantly, train of thought).

Would it be possible to use machine learning tools to teach a bot to trade the same way? Let's say you can code basic trading and money management rules, but need to add context related filters which cannot be easily put into code (the discretionary part).

If we are talking about day trading (3-6 trades a day) would it take just a few years to get close enough?

Yup, you can do much more than that.

Here's a read that can provide you some food for thought: https://blog.quantinsti.com/artificial-intelligence-machine-learning-trading/

Of course, this was just a beginner-level blog to help you understand the scheme of things.

Hope it helps!

 

[billsimons]

您首先需要知道交易员在交易决策中的行为使用了哪些输入，并尽量减少这些输入。例如，如果交易员完全基于价格进行裸交易而不受胎儿影响，或者存在影响交易的基本面分析或新闻。然后，您可以将这些最小输入输入到深度学习网络中，以产生与交易员进行的相同交易的结果。但是，如果有人还没有尝试过这样，我会感到惊讶：）

I’m currently using machine learning for price prediction.