2

My crime classification dataset has indicator features, such as has_rifle.

The job is to train and predict whether data points are criminals or not. The metric is weighted mean absolute error, where if the person is criminal, and the model predicts him/her as not, then the weight is large as 5. If person is not criminal and the model predicts as he/she is, then weight is 1. Otherwise the model predicts correctly, with weight 0.

I've used classif:multinom method in mlr in R, and tuned the threshold to 1/6. The result is not that good. Adaboost is slightly better. Though neither is perfect.

I'm wondering which method is typically used in this kind of binary classification problem with a sparse {0,1} matrix? And how to improve the performance measured by the weighted mean absolute error metric?

Has QUIT--Anony-Mousse
  • 76,138
  • 12
  • 138
  • 194
j20120307
  • 71
  • 2
  • 8
  • I think it's better to ask that question on http://stats.stackexchange.com/questions or http://datascience.stackexchange.com/users/13936 – Anton Protopopov Mar 25 '16 at 09:40
  • 1
    You could look at this cheat-sheet : http://scikit-learn.org/stable/tutorial/machine_learning_map/index.html even though you're not coding in python. – Till Mar 25 '16 at 10:26

1 Answers1

0

Dealing with sparse data is not a trivial task. Lack of information makes difficult to capture features such as variance. I would suggest you to search for subspace clustering methods or to be more specific, soft subspace clustering. The last one usually identifies relevant/irrelevant data dimensions. It is a good approach when you want to improve classification accuracy.

Victor Oliveira Antonino
  • 988
  • 1
  • 9
  • 26