For Assignment 5, you will be developing classification models to predict which passengers survived the sinking of the Titanic. In the data section of this page, you will find a labeled training set (Lab5_train.csv) and an unlabelled test set (Lab5_test.csv). To start off the assignment, you will form groups of
2 to 5
. As a group, you will then be selecting models (i.e. choosing an algorithm, tuning parameters, etc) using the training set, then submitting predictions for the test set in the specified format.
The competition will be conducted in two phases. During
Phase 1 (02/23 - 03/02)
, each group is required to make at least
4 submissions
from at least
2 different algorithms
(like svm, neural networks, decision trees, or others that we have not directly used in class - but no ensemble models). Each group is allowed
two submissions per day
.
During
Phase 2 (03/03 - 03/12)
, each team should work on developing an
ensemble model
. You can start Phase 2 as soon as your team is happy with the individual algorithms, but make sure each group has completed the Phase 1 requirements first.
See the evaluation section of this site for details on scoring.
Acknowledgements
This is based on the Kaggle's popular Titanic competition.