After a semester of learning linear models, we setup this competition to encourage participates to apply their learned methods to real data.  In class, we have learn the theory and mathematics. Now it is the time to get familiar with the real application!!  The competition helps you to get started fast.

Here are some suggestions:
1. In the real world, it is not sufficient to fit your model directly to the data. Try to do some exploratory data analysis (EDA) before you fitting the model, which may help you pass through the baseline (See Score). 
2. More often than not, "pure linear" models may not be useful.  But a too complicated model  also easily performs awfully for prediction in the test set.  
3. Usually, we have to try several candidate models, and select a final one. This competition allows you to upload two final models, and we count your best one.

Enjoy and have fun!!