Awesome
<img src='https://s3.amazonaws.com/drivendata-public-assets/logo-white-blue.png' width='600'> <br><br>
Countable Care: Modeling Women's Care Decisions
Goal of the Competition
Recent literature suggests that the demand for women’s health care will grow over 6% by 2020. Given how rapidly the health landscape has been changing over the last 15 years, it’s increasingly important that we understand how these changes affect what care people receive, where they go for it, and how they pay. Through the National Survey of Family Growth, the CDC provides one of the few nationally representative datasets that dives deep into the questions that women face when thinking about their health.
Can you predict what drives women’s health care decisions in America?
What's in this Repository
This repository contains code volunteered from leading competitors in the Countable Care: Modeling Women's Health Care Decisions on DrivenData. Code for all winning solutions are open source under the MIT License.
Winning code for other DrivenData competitions is available in the competition-winners repository.
Winning Submissions
Place | Team or User | Public Score | Private Score | Summary of Model |
---|---|---|---|---|
1 | giba | 0.2482 | 0.2539 | I decided to quit using a simple feature selection and use the ensemble technique to better explore feature interaction between all features and different learning techniques. |
2 | 1aguschin | 0.2492 | 0.2543 | Stacking is a technique of combining predictions of different classifiers in new meta-classifier. After averaging predictions received with different random splits we are making new meta-feature which will be used in our meta-classifier |
3 | JYL | 0.2497 | 0.2549 | Our approach is the ensemble of 20 individual classifiers with various algorithms and features. |
Winner's Interview: Gilberto Titericz