In predictive analytics, we want to predict classes for
new data (e.g. cats vs. dogs), or predict future values of a
time series (e.g. forecast sales for next month). We build
models on existing data, and hope they extend, or
generalize, to the future. In
supervised learning, we have data from the past with all the
predictor values and the true values we wish to predict. Although
defining the business problem, gathering relevant data, cleaning
and preparing the data, and...
