Kaggle Mini Competition 1 : Regression challenge
This is the first mini competition that you will be participating in for CSCI 4622. In this competition you will work with a dataset to predict house sale prices in King County, USA. This is a simple clean dataset in which you will use the 20 available features to predict the sale price. Training and validation data are available in the 'Data' tab.
Remember:
You should be working in teams of 2-3 people. You are not required to physically code together but you are encouraged to try different things and select the best model you'd like to submit.
Competition is open from Friday (2/7/2020) at 2 PM to Wednesday (2/12/2020) at Midnight.
Your grade on all the mini competitions account for 20% of your total grade
How does this work?
Your goal in this exercise is to build the best model, as a team, to predict the housing sale prices in this dataset (more information in the Data tab). How you code and work as a team is upto you: you can all work on the same code and divide work, or build different models and ensemble amongs them, or any other method you prefer. Once you build the model, you need to upload your submissions (refer to sample_submission.txt in the Data tab). You will have access to labelled training data and unlabelled validation data. Your model will be evaluated based on the root mean squared error (RMSE) obtained on this validation data.
Based on your RMSE score, you will be assigned a rank on the Kaggle Leaderboard. This way you are able to monitor your standing in this competition.  Once the competition is closed, the person at the top of the leaderboard is the winner. But wait, there's a twist. We will hold out an additional subset of the data that your model will be evaluated on. You will be unable to see the scores on this set until the competition closes. This means rankings can change when the competition closes. Therefore, though you try to improve your rankings, remember to keep your model generalizable so that you can have the last laugh.
Deliverables a.k.a what you will be graded on
Your code(s)
Short one or two page report summarizing everything you did to build your best model. It is recommended that you limit it to one page unless there is something you really want to mention that can't be fit. (You must submit a report in order to get a grade)