Taylor A. Jean-Jacques: using machine learning to predict life outcomes

Wednesday, Oct 28, 2020
by Sharon Adarlo

Taylor A. Jean-Jacques, 22, Class of 2020


Taylor A. Jean-Jacques majored in psychology and earned the undergraduate certificate in Statistics and Machine Learning from the Center for Statistics and Machine Learning (CSML).


Jean-Jacques has had a long running interest in coding, computer science and technology. She taught herself to code when she was 14; for two summers, she was a software mobile engineer intern for Facebook where she worked on the advertising and Instagram teams. Later, Jean-Jacques became interested in machine learning, hence her enrollment in the CSML certificate.

“There is a lot of overlap with psychology and machine learning, particularly when it comes to artificial intelligence and machine learning. My thesis falls within this overlap,” said Jean-Jacques, whose advisor is Tom Griffiths, the Henry R. Luce Professor of Information Technology, Consciousness, and Culture of Psychology and Computer Science.

Jean-Jacques’s independent project for her CSML certificate focused on developing a machine learning model to predict life outcomes of people. This model was based on data from the Fragile Families and Child Wellbeing study, which is a joint effort between Princeton and Columbia universities. The study follows a cohort of nearly 5,000 children born in major U.S. cities between 1998 and 2000.

“I was looking to build accurate model for predicting six different outcomes,” said Jean-Jacques. “Those outcomes are child GPA, material hardship, grit, job training, family eviction and job layoff.”

“My approach relies on existing data science techniques -- imputation of missing data, elimination of low variance features, prediction via ridge and logistic regression models -- and proposes and evaluates a new model -- a neural network pre-trained on synthetic data created from Gaussian noise,” said Jean-Jacques. “This approach creates a flexible model with reasonable bias for human behavior and enhanced predictive power. Results revealed that the proposed model outperformed benchmark models for four of the six outcomes by up to 28% and outperformed existing researchers’ models for grit and GPA by up to 40%.”

After she graduated, Jean-Jacques started working as a technology investment banking analyst for JPMorgan Chase & Co. She was accepted to Harvard Business School for deferred admission during her senior year, and plans to enroll after acquiring industry experience. As for her other work experience, she was an investment analyst intern at Fidelity Investments and a software mobile engineer intern for Facebook.

Extracurricular Activities:

Jean-Jacques was on the board of trustees for the University Store, was the business manager for the Daily Princetonian, and was part of the school rowing team in her freshman and sophomore years.

For Fun:

Jean-Jacques loves playing sports with friends.