i'm not like other girls, they get unwanted advances in their DMs, i getpic.twitter.com/RCEQczitTl
Show this thread
-
I guess when I think of a high vs low vol regime, I'd think of it more as a continuous block of time where there's largely increased rvol, but may have quiescent periods in between. I feel your method makes sense but you'd definitely end up with a lot more regime switching
That depends on what the timescales of the two moving averages are and how much you buffer it. Obviously still need to choose values for these hyperparams, but they are simple and intuitive to choose (i.e. they don't need to be fitted)
-
-
how do you choose the moving average lengths/buffer without overfitting to the dataset? pretty new to all this quant stuff so i'm not sure where to start with choosing the hyperparameters
-
I just pick some sane semantic parameters (e.g. 5, 7, 30 day) but other approaches (h/t
@thodoha I’ve seen are using multiple and averaging performance to reduce timing bias. - Show replies
New conversation -
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.