Prediction Models and Data Analysis

The syllabus says that the rest of the class is about

understanding the how “data analysis/ML/«buzz word #51»” fit into the bigger picture of producing and using knowledge.* to quote Prof Gunther: data < info < knowledge < wisdom

what we’re going to do with the data. executing and improving a model. applied econometrics (ie more conceptual than mathematical rigor) to understand and improve the output

learning from the model: what does the output of my analysis mean? (A and B are related, but WHY)

So that's what we're going to do. We have enough raw tools and you should have (nearly) completed your first farm-to-table analysis (scrap, clean, and process the data) for Assignment 5.

Over the next month, we going to cover

• regression (how-to, why-to, and what it "means")
• boosted regression trees
• clustering algorithms
• natural language processing
• the whole time, we're going to stay focused on "WHY" we are doing what we are doing rather than just flying ahead blind

This should be fun!