User aranglol

34 votes

Accepted

Lightgbm vs xgboost vs catboost

answered Apr 19, 2019 at 23:08

16 votes

Accepted

Why class weight is outperforming oversampling?

answered May 26, 2019 at 20:18

10 votes

What is the outcome of a Cox regression in xgboost?

answered May 17, 2019 at 3:47

8 votes

Accepted

What's the point of the test set?

answered Apr 19, 2019 at 21:58

8 votes

Accepted

XGBoost: # rounds is equal to n_estimators?

answered Aug 26, 2019 at 19:36

7 votes

Accepted

Why is there a trade-off between bias and variance in supervised learning? Why can't we have best of both worlds?

answered Aug 28, 2019 at 4:50

7 votes

Accepted

Python XGBoost predict_proba returns very high or low probabilities

answered Jul 19, 2019 at 14:27

5 votes

Accepted

What predictive model to use to impute Gender?

answered May 7, 2019 at 23:18

4 votes

Accepted

How to optimize hyperparameters in stacked model?

answered Jul 29, 2019 at 23:55

4 votes

Accepted

Is there a Feature selection process for ARIMA model?

answered Jun 3, 2019 at 23:51

4 votes

Why does Lasso behave "erratically" when the number of features is greater than the number of training instances?

answered Jul 17, 2019 at 13:44

4 votes

why naive is needed in Naive Bayes ,what happens if naive is not included in Bayes theorem?

answered Feb 18, 2020 at 20:48

3 votes

Which comes first? Multiple Imputation, Splitting into train/test, or Standardization/Normalization

answered Jun 3, 2019 at 16:31

3 votes

Accepted

In Naive Bayes classifier how is P(sneezing,builder|flu) = P(sneezing|flu)P(builder|flu)?

answered Jul 8, 2019 at 16:47

3 votes

Accepted

Prediction interval for general non-linear regression

answered May 3, 2019 at 0:59

3 votes

Large negative R2 or accuracy scores for random forest with GridSearchCV but not train_test_split

answered May 16, 2019 at 4:31

2 votes

Estimating test AUC using k-fold CV for imbalanced classification problem

answered May 3, 2019 at 15:44

2 votes

Can `k=1` be a good choice for K neighbors classification?

answered Apr 20, 2019 at 19:34

2 votes

Accepted

Am I using GridSearch correctly or do I need to use all data for cross validation?

answered May 12, 2019 at 19:12

2 votes

Can I add features that are parts of another feature?

answered May 29, 2019 at 19:07

2 votes

Accepted

Feature Selection with one-hot-encoded categorical data

answered Jun 2, 2019 at 20:47

2 votes

Accepted

Automatically uses several cores on R

answered Jun 6, 2019 at 1:32

2 votes

What is the purpose of Logit function? At what stage of model building process this logit function is used?

answered Jun 8, 2019 at 0:59

2 votes

Find causal relations between multiple branches of science

answered Jun 24, 2020 at 9:57

2 votes

xgboost feature selection and feature importance

answered Aug 30, 2019 at 2:14

2 votes

Accepted

Choosing best model produced from different algorithms. Metric produced by cross-validation on the train set or metric produced on the test set?

answered Feb 15, 2021 at 5:05

2 votes

ACF vs PACF in ARIMA

answered Aug 20, 2019 at 4:16

2 votes

Accepted

Xgboost multiclass monotonic constraints

answered Dec 21, 2023 at 18:24

2 votes

Accepted

Calculate the best alpha, beta and gamma that should be used in the holt-winters exponential smoothing formula

answered Jan 31, 2024 at 3:09

2 votes

Is there a way to check if a time-series is seasonal without manual inspection of its decomposition?

answered Jan 31, 2024 at 23:56

Stack Exchange Network

62 Answers

Lightgbm vs xgboost vs catboost

Why class weight is outperforming oversampling?

What is the outcome of a Cox regression in xgboost?

What's the point of the test set?

XGBoost: # rounds is equal to n_estimators?

Why is there a trade-off between bias and variance in supervised learning? Why can't we have best of both worlds?

Python XGBoost predict_proba returns very high or low probabilities

What predictive model to use to impute Gender?

How to optimize hyperparameters in stacked model?

Is there a Feature selection process for ARIMA model?

Why does Lasso behave "erratically" when the number of features is greater than the number of training instances?

why naive is needed in Naive Bayes ,what happens if naive is not included in Bayes theorem?

Which comes first? Multiple Imputation, Splitting into train/test, or Standardization/Normalization

In Naive Bayes classifier how is P(sneezing,builder|flu) = P(sneezing|flu)P(builder|flu)?

Prediction interval for general non-linear regression

Large negative R2 or accuracy scores for random forest with GridSearchCV but not train_test_split

Estimating test AUC using k-fold CV for imbalanced classification problem

Can `k=1` be a good choice for K neighbors classification?

Am I using GridSearch correctly or do I need to use all data for cross validation?

Can I add features that are parts of another feature?

Feature Selection with one-hot-encoded categorical data

Automatically uses several cores on R

What is the purpose of Logit function? At what stage of model building process this logit function is used?

Find causal relations between multiple branches of science

xgboost feature selection and feature importance

Choosing best model produced from different algorithms. Metric produced by cross-validation on the train set or metric produced on the test set?

ACF vs PACF in ARIMA

Xgboost multiclass monotonic constraints

Calculate the best alpha, beta and gamma that should be used in the holt-winters exponential smoothing formula

Is there a way to check if a time-series is seasonal without manual inspection of its decomposition?