Measuring the predictability of life outcomes with a scientific mass collaboration

Abstract

How predictable are life trajectories? We investigated this question with a scientific mass collaboration using the common task method; 160 teams built predictive models for six life outcomes using data from the Fragile Families and Child Wellbeing Study, a high-quality birth cohort study. Despite using a rich dataset and applying machine-learning methods optimized for prediction, the best predictions were not very accurate and were only slightly better than those from a simple benchmark model. Within each outcome, prediction error was strongly associated with the family being predicted and weakly associated with the technique used to generate the prediction. Overall, these results suggest practical limits to the predictability of life outcomes in some settings and illustrate the value of mass collaborations in the social sciences.

Document Details

Document Type
Pub Defense Publication
Publication Date
Mar 30, 2020
Source ID
10.1073/pnas.1915006117

Entities

People

  • Abdulla Alhajri
  • Abdullah Almaatouq
  • Adaner Usmani
  • Ahmed Musse
  • Alex Pentland
  • Alexander T. Kindel
  • Allison C Morgan
  • Anahit Sargsyan
  • Andrew E. Mack
  • Andrew Halpern-manners
  • Andrew Or
  • Anna Filippova
  • Antje Kirchner
  • Areg Karapetyan
  • Arvind Narayanan
  • Austin van Loon
  • Barbara E. Engelhardt
  • Bedoor Alshebli
  • Ben Leizman
  • Ben Sender
  • Bernie Hogan
  • Bingyu Zhao
  • Bo-ryehn Chung
  • Brandon M. Stewart
  • Brian J. Goode
  • Bryan Schonfeld
  • Caitlin E. Ahearn
  • Catherine Wu
  • Chenyun Zhu
  • Claudia V. Roberts
  • Connor Gilroy
  • Crystal Qian
  • Daniel E. Rigobon
  • David Jurgens
  • Dean Knox
  • Debanjan Datta
  • Diana M. Stanescu
  • Diana Mercado-garcia
  • Drew M Altschul
  • Duncan J. Watts
  • E. H. Kim
  • Eaman Jahani
  • Emma Tsurkov
  • Erik H. Wang
  • Ethan Porter
  • Flora Wang
  • Gregory Faletto
  • Guanhua He
  • Hamidreza Omidvar
  • Helge Marahrens
  • Ian Lundberg
  • Ilana M. Horwitz
  • James Wu
  • Jeanne Brooks-gunn
  • Jennie E. Brand
  • Jeremy Freese
  • Jingwen Yin
  • Jonathan D. Tang
  • Josh Gagné
  • Julia Wang
  • Karen Levy
  • Karen Ouyang
  • Katariina Mueller-gastell
  • Katy M. Pinto
  • Kengran Yang
  • Khaled Al-ghoneim
  • Kimberly Higuera
  • Kirstie Whitaker
  • Kivan Polimis
  • Kristin E. Porter
  • Kun Jin
  • Landon Schnabel
  • Lisa M. Hummel
  • Lisa P Argyle
  • Livia Baer-bositis
  • Louis Raes
  • Malte Möser
  • Maria K. Wolters
  • Matthew J. Salganik
  • Mayank Mahajan
  • Moritz Büchi
  • Moritz Hardt
  • Muna Adem
  • Naijia Liu
  • Naman Jain
  • Nicole Bohme Carnegie
  • Noah Mandell
  • Onur Varol
  • Patrick Kaminski
  • Qiankun Niu
  • Redwane Amin
  • Ridhi Kashyap
  • Ryan B. Amos
  • Ryan James Compton
  • Samantha Weissman
  • Sara Mclanahan
  • Sonia Hausen
  • Sonia P. Hashim
  • Stephen McKay
  • Tamkinat Rauf
  • Tejomay Gadgil
  • Thomas Davidson
  • Thomas Schaffner
  • Viola Mocz
  • Wei Lee Woon
  • William Eggert
  • William Nowak
  • Xiafei Wang
  • Yoshihiko Suhara
  • Yue Gao
  • Zhi Wang
  • Zhilin Fan

Organizations

  • Alan Turing Institute
  • Brigham Young University
  • California State University
  • Columbia University
  • Cornell University
  • Dataiku
  • Engineering and Physical Sciences Research Council
  • Eunice Kennedy Shriver National Institute of Child Health and Human Development
  • Expedia Group
  • George Washington University
  • GitHub
  • Harvard University
  • Indiana University
  • Institute of Education Sciences
  • Khalifa University
  • Kyoto University
  • Massachusetts Institute of Technology
  • Montana State University
  • National Institutes of Health
  • National Science Foundation
  • New York University
  • New York University Abu Dhabi
  • Northeastern University
  • Ohio State University
  • Princeton University
  • Russell Sage Foundation
  • Stanford University
  • Syracuse University
  • Tilburg University
  • University of California
  • University of California, Santa Cruz
  • University of Cambridge
  • University of Colorado
  • University of Edinburgh
  • University of Lincoln
  • University of Michigan
  • University of Oxford
  • University of Pennsylvania
  • University of Southern California
  • University of Washington
  • University of Zurich
  • Virginia Tech

Tags

Readers

  • Mental Health of Military Veterans with Posttraumatic Stress Disorder (PTSD): Risk Factors, Prevalence, Symptoms, and Treatment.
  • Neural Network Machine Learning.
  • Ocean-Atmosphere Mesoscale Modeling, Data Assimilation, and Flux Boundary Layers

Technology Areas

  • AI & ML
  • AI & ML - Bayesian Inference
  • AI & ML - Neural Networks