Skip to main content
Data Science

You are not logged in. Your edit will be placed in a queue until it is peer reviewed.

We welcome edits that make the post easier to understand and more valuable for readers. Because community members review edits, please try to make the post substantially better than how you found it, for example, by fixing grammar or adding additional resources and hyperlinks.

3
  • $\begingroup$ I still find it shocking that there would be perfect out-of-sample predictions like $R^2=0$ means, and that makes me believe there to be a bug in the code (somewhere). $\endgroup$ Commented Dec 20, 2023 at 15:19
  • $\begingroup$ @Dave: Do you mean an R-squared of 1? Yes, it is peculiar - I obtained an R-squared of 0.97 when I ran the model across daily data for the same period. I note that the author is calculating RSI using a 14-day window of the adjusted closing price, it might be the case that the closing price at time t is also included among the values in the RSI window which is artificially inflating the R-Squared. $\endgroup$ Commented Dec 21, 2023 at 23:09
  • $\begingroup$ Yes, I meant $R^2 = 1$ for perfect predictions. Your speculation that the outcome (somehow) makes it into the feature set would explain this, though any practical use of such a model would require a time machine. $\endgroup$ Commented Dec 22, 2023 at 14:39