Cross Validated
Sponsored by
Sponsored logo

Popular Question

 Popular Question
Question with 1,000 views. This badge can be awarded multiple times.

earned this badge 18 times.
Why would somebody use a hash function for creating a test/train split instead of random seed?
Awarded Jun 21 at 11:33
Why is gradient descent not used for ARIMA model estimation?
Awarded Jun 18 at 8:43
If an auto-regressive time series model is non-linear, does it still require stationarity?
Awarded Dec 8 '19 at 22:10
How does logistic regression “elegantly” handle unbalanced classes?
Awarded Oct 28 '19 at 8:45
How does neural network auto-regression produce multistep forecasts?
Awarded Sep 13 '19 at 8:25
When is the AIC a good model selection criterion for forecasting and when is it not?
Awarded Jul 23 '19 at 6:00
How can a network with only ReLU nodes output negative values?
Awarded Jun 20 '19 at 16:50
In a regression model, why does adding variables increase $R^2$ and decrease the SSE? [duplicate]
Awarded Jun 7 '19 at 12:40
How would one use KDE as a one 1D clustering method?
Awarded Apr 30 '19 at 1:15
How far ahead are ARIMA and Exponential smoothing useful?
Awarded Feb 25 '19 at 21:00
Why is Maximum Likelihood used for ARIMA instead of least squares?
Awarded Jan 16 '19 at 22:15
Can one force an ARIMA forecast to be positive?
Awarded Dec 28 '18 at 6:20
Which loss function to use when training LSTM for time series?
Awarded Dec 13 '18 at 18:30
Does the universal approximation theorem for neural networks hold for any activation function?
Awarded Dec 11 '18 at 6:20
ARIMA vs Exponential Smoothing in demand forecasting: Why would someone choose ES over ARIMA?
Awarded Nov 13 '18 at 19:35
How to handle a “self defeating” prediction model?
Awarded Oct 23 '18 at 10:45
Why doesn't regularization solve Deep Neural Nets hunger for data?
Awarded May 13 '18 at 1:00
Statsmodels says ARIMA is not appropriate because series is not stationary, how is it testing that?
Awarded Dec 10 '17 at 12:22

Others with this badge