Can I read Predicting San Francisco Crimes with ML on EtoBox?

Predicting San Francisco Crimes with ML by Teodor von Burg is a document available to read on EtoBox.

What is Predicting San Francisco Crimes with ML about?

The document discusses using a Naive Bayes classifier to predict the category of crimes in San Francisco based on time and location. It outlines loading and preprocessing the data, which includes converting categorical variables to binary variables. An initial model using day of week and police district achieved a log loss of 2.62. Adding hour of day as a feature improved the score to 2.58. This approach resulted in a final rank of 76th out of 226 competitors in the Kaggle competition.

Author

Teodor von Burg

Language

EN