Pinned Tweet
Machine learning for finance is hard.
So let's take a step-by-step case study in this 🧵
This time - let's ask ML to find patterns without giving it any direction, and use those patterns to mitigate risk.
Oh, and we'll backtest the ML model too!
Enjoy!
An ML idea for trading:
• Cluster to find patterns
• Fit a classifier using your clusters as labels
• Use SHAP to explain what features are important per cluster
Explainable, unsupervised learning!
Perhaps I'll make a 🧵about this soon!
The two data providers I am currently using:
• Polygon.io
• Financial Modelling Prep
Both on their cheapest plan (for now).
Pros and cons of both on the starter plan⬇️
If you pay for the more expensive packages you get extra perks (e.g. less rate limiting, live data etc)
And there are plenty of other data providers out there.
But these two are great options if you're looking for something cheap (like me!).
1
3
2,362
Anyway, that's all for this one - I hope you found this very short list of pros/cons useful!
And if you are interested in applying ML/data-science to finance then follow me @DrDanobi for more posts like these!
The two data providers I am currently using:
• Polygon.io
• Financial Modelling Prep
Both on their cheapest plan (for now).
Pros and cons of both on the starter plan⬇️
1
2
2,422
Simple ML idea for finance
Clustering for stop-loss setting:
• Use kmeans to group similar trades
• Per cluster, get the x% quantile for the move in the opposite direction for winners only
This may help keep you in similar looking winners for future events - worth a test!
One key thing I have recently learned about classification models:
It's not just about being right
It's about accurately gauging how likely the model is right!
This is where we can use one cool technique - probability calibration.
Let's explore in this short 🧵
Honestly, this topic goes way deeper than this, and it's all interesting stuff.
But honestly, it's probably article worthy rather than 🧵material!
Nevertheless, hopefully this gives the real basic principles for you to work off.
1
1
1,437
Anyway, that's all for this one - I hope you found this very short 🧵 useful!
And if you are interested in applying ML/data-science to finance then follow me @DrDanobi for more threads like these!
One key thing I have recently learned about classification models:
It's not just about being right
It's about accurately gauging how likely the model is right!
This is where we can use one cool technique - probability calibration.
Let's explore in this short 🧵
5
1,703



