Published Mar 27, 2023

CAREER Prediction

Dive into cutting-edge career prediction with Keyon Vafa as he unveils a machine learning model that leverages perplexity and transfer learning, emphasizing interdisciplinary collaboration and the complexity of analyzing longitudinal survey data to advance labor economics.

Episode Highlights

Topics covered

Evaluating Model Performance
01
Interdisciplinary Collaboration
02
Career Prediction
03

CAREER Prediction

Topics covered

Popular Clips

Predicting Career Trajectories

Longitudinal Survey Data Sets

Notion AI Revolution

Challenges in Social Science Surveys

Improving Predictive Models

Survey Data Challenges

Evaluating Model Metrics

Data Connect Conference

Transfer Learning Insights

Transfer Learning Applications

Predicting Job Transitions

Predictive Improvements

Predicting Occupational Trajectories

Analyzing Job Data

Episode Highlights

Evaluating Model Performance

Interdisciplinary Collaboration

Career Prediction

CAREER Prediction

Topics covered

Popular Clips

Episode Highlights

Evaluating Model PerformanceKeyon Vafa explores the intricacies of evaluating and improving a machine-learning model for career prediction. He highlights the use of perplexity as a key metric and the role of transfer learning in enhancing predictive accuracy.

Evaluating Model Performance

Interdisciplinary CollaborationKeyon Vafa discusses the collaborative efforts and interdisciplinary approach behind a machine-learning model for career prediction. The project utilizes longitudinal survey data and transfer learning to enhance predictions in labor economics and beyond.

Interdisciplinary Collaboration

Career PredictionKeyon Vafa, a computer science Ph.D. student at Columbia University, discusses his research on a machine-learning model for career prediction. He elaborates on the model's methodology, the role of transfer learning, and the challenges of using survey data.

Career Prediction