Welcome to the DAT158 assignment 1 competition! Click here to enter.
You'll work in teams trying to create machine learning models for predicting house prices.
The competition is based on the data set studied in Chapter 2 of the course text book. You'll learn everything you need to get started by reading through that chapter.
The machine learning project checklist described in Chapter 2 and Appendix B is a useful guide through realistic machine learning projects:
- Frame the problem and look at the big picture
- Get the data
- Explore the data to gain insights
- Prepare the data to better expose the underlying data patterns to machine learning algorithms
- Explore many different models and short-list the best ones
- Fine-tune your models and combine them into a great solution
- Present your solution
- Launch, monitor and maintain your system
In this assignment you're asked to (i) produce a score on the Kaggle competition leaderboard, (ii) upload the code used to get the score either as a Kaggle Kernel or as a .ipynb file here on Canvas, (iii) present your work (as a team) to a teacher or TA in a short 12 minute oral presentation.
Note that you can submit multiple predictions to the leaderboard. You should make a first submission to the Kaggle leaderboard as soon as possible to familiarize yourself with how Kaggle works. And then work to improve the score.
The notebook you'll submit has to have both comments and code structured after the 8 steps listed above. Include enough explanatory text to make your notebook instructive and useful for interested people who haven't read the textbook. You don't have to include code under Step 1, 7 and 8, but you should give short text summaries of the main ideas.
You encouraged to collaborate with others.
You can write your notebook in English or Norwegian.
The oral presentations will take place on Monday September 23, 08.15–10.00. You will be assigned a time-slot and a room after the assignment submission deadline.
Note that the deadline is final. To be able to take the exam in DAT158 you have to submit your assignment before the deadline (unless you can document valid reasons for failing to meet the deadline, for example a note from your doctor). If your submission and subsequent oral presentation is graded as not sufficient to pass, you will get one more chance, with one week from receiving notification of failure as the new deadline. This is your last chance. If you do not pass you will not be able to take the exam.
Here's a link to the presentation schedule for Monday, September 23: