Friendly reminder to my data scientists that if you randomize train/test data on financial time series data you should probably re-evaluate your life choices
Replying to @nope_its_lily
Depends on the time series, but block cross validation can be okay for some use cases (though obviously only walk-forward gives you anything like a true picture of how your model would perform in a live environment)
11:40 AM - 27 Feb 2021
0 replies
0 retweets
12 likes
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.