Data Preparation

  • Roger Barga
  • Valentine Fontama
  • Wee Hyong Tok
Chapter

Abstract

Machine learning can feel magical. You provide Azure ML with training data, select an appropriate leaning algorithm, and it can learn patterns in that data. In many cases, the performance of the model that you build, if done correctly, will outperform a human expert. But, like so many problems in the world, there is a significant “garbage in, garbage out” aspect to machine learning. If the data you give it is rubbish, the learning algorithm is unlikely to be able to overcome it. Machine learning can’t perform “data alchemy” and turn data lead into gold; that’s why we practice good data science, and first clean and enhance the data so that the learning algorithm can do its magic. Done correctly, it’s the perfect collaboration between data scientist and machine learning algorithms.

Keywords

Machine Learning Feature Selection Class Label Credit Risk Machine Learning Algorithm 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
This is a preview of subscription content, log in to check access

Copyright information

© Roger Barga, Valentine Fontama, and Wee Hyong Tok 2015

Authors and Affiliations

  • Roger Barga
    • 1
  • Valentine Fontama
    • 1
  • Wee Hyong Tok
    • 1
  1. 1.WAUS

Personalised recommendations