Cross Validated
Meta user
Network profile
5,306
reputation
21
28

Soren Havelund Welling

Independant Consultant

CRAN package forestFloor, to visualize the mapping structure of random forests

interests: Physical Chemistry, Oral protein delivery, pharmaceuticals, QSAR models, molecular descriptors, Forecasting financial trends with machine learning, R coding

98
answers
0
questions
~458k
people reached
  • Copenhagen, Denmark
  • sorhawell
  • forestfloor.dk
  • Member for 5 years, 1 month
  • 1,151 profile views
  • Last seen Aug 14 at 8:55

Communities (9)

Top network posts

Top tags (76)

Score 378
Posts 82
Posts % 84
Score 203
Posts 33
Score 170
Posts 35
Score 98
Posts 13
Score 56
Posts 13
Score 39
Posts 6
View all tags →

Top posts (98) All Questions Answers | Votes Newest

51 Obtaining knowledge from a random forest Sep 16 '15
29 In a random forest, is larger %IncMSE better or worse? Jul 22 '15
28 R package for Weighted Random Forest? classwt option? Jun 21 '15
26 How to interpret Mean Decrease in Accuracy and Mean Decrease GINI in Random Forest models Feb 22 '16
19 Why log-transforming the data before performing principal component analysis? Aug 2 '15
18 Won't highly-correlated variables in random forest distort accuracy and feature-selection? Apr 3 '15
16 Does Breiman's random forest use information gain or Gini index? Aug 14 '15
11 How are Random Forests not sensitive to outliers? Dec 19 '15
8 CART: Selection of best predictor for splitting when gains in impurity decrease are equal? Aug 13 '15
7 Random forest in R using unbalanced data Aug 23 '15
View all questions and answers →

Badges (49)

Gold

—

Silver

21

Rarest

Bronze

28

Rarest

View all badges →