Winning Models for GPA, Grit, and Layoff in the Fragile Families Challenge
Our team--The Pentlandians Ensemble--from MIT has won first place in three categories in the Fragile Families Challenge (FFC). The Challenge is a Kaggle-like competition based on the Fragile Families and Child Wellbeing Study, which followed thousands of American families for more than 15 years, collecting information about the children, their parents, their schools, and their overall environments.
As participants in the Challenge, we were asked to use this information in a new way. With all the background data from birth to age nine (approximately 12,000 features), and known outcomes at age 15 for a small portion of the children as training data, we were tasked with predicting outcomes in the following six key categories:
- Grade point average (academic achievement) of the children
- Grit (passion and perseverance) of the children
- Material hardship of the household (a measure of extreme poverty)
- Eviction of the families (for not paying the rent or mortgage)
- Layoff of the caregiver
- Job training (if the primary caregiver would participate in a job skills program).
More than 150 teams from around the world submitted over 3,000 predictive models. Our submission was ranked first in predicting GPA, grit, and layoffs, and was ranked 3rd for job training, 8th for material hardship, and 11th for eviction.
Our team consisted of myself, Eaman Jahani, Daniel Rigobon, Yoshihiko Suhara, Khaled Al-Ghoneim, and Abdulaziz Alghunaim. A paper discussing and analyzing our approach to the Fragile Families Challenge will appear in a special issue of Socius, the open-access journal published by the American Sociological Association.
RELATED AND SELECTED CONTENT:
A Paper detailing our approach (preprint): Winning Models for GPA, Grit, and Layoff in the Fragile Families Challenge