/* ---- Google Analytics Code Below */

Saturday, September 27, 2014

Feature Engineering as the Basis of Analytics

Very good informal and non technical look at feature engineering.   It is part of any analytic process, sometimes obvious, but also sometimes subtle. My definition:  It's adjusting the data and decision problem you have to the tools available,  that can then create a useful and accurate solution.  Or as the article suggests:  " ... Feature engineering is the process of transforming raw data into features that better represent the underlying problem to the predictive models, resulting in improved model accuracy on unseen data. ... " .  I never called it 'feature engineering',  but rather 'Modeling' but it was always a key aspect of any analytics effort we did.

No comments: