Prescriptive Analytics
A system that recommends without a declared objective has one anyway — chosen by whoever wrote the code, and invisible to everyone else.
-
-
Loss Functions
Twenty-five contaminating values pulled the squared-error fit from 99.73 to 142.60, while absolute error stayed at 100.02 and Huber at 100.21.
-
Optimization for Machine Learning
Fitting a model means minimizing something. The objective’s geometry decides everything else.