Data Driven Fitting with MATLAB

Register to watch video

In this webinar, you will learn how to do data driven fitting with MathWorks products.
Data driven fitting derives all of the information required to generate a model directly from the data set.  Data driven fitting is also referred to as “black box” modeling and nonparametric fitting.

Applied examples from the webinar include: 

  • Comparing the accuracy of different fitting techniques
  • Using back-testing to measure the accuracy of your model
  • Generating confidence intervals with bootstrap
  • Using cross validation to avoid overfitting

Key analytical techniques include:

  • Neural Networks
  • Boosted and bagged decision trees
  • Localized regression
  • Smoothing splines

View the MATLAB code

About the Presenter: Richard Willey is a product marketing manager focused on MATLAB and add-on products for data analysis, statistics, and curve fitting. Prior to joining MathWorks in 2007, Richard worked at Wind River Systems and Symantec. Richard has a dual masters in engineering and management from the Massachusetts Institute of Technology and a master’s degree in economics from Indiana University.

Product Focus

  • Curve Fitting Toolbox
  • Neural Network Toolbox
  • Statistics Toolbox

Recorded: 14 Aug 2012