Predicting the time to get back to work using statistical models and machine learning approaches

George Bouliotis, M Underwood, R Froud · 2024

Read Predicting the time to get back to work using statistical models and machine learning approaches by George Bouliotis, M Underwood, R Froud (2024) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-11606207.txt.

Description

George Bouliotis, Martin Underwood, and Robert Froud compare ways to guess when jobless folk return to work in a 2024 study. The data come from a UK program that aids families with complex needs. Records held 61 yes-no facts on 3,161 people who took part. The team fit classic survival models and three machine learning rivals to the same data. Half the group found a first job in about 254 days.

No method won by a wide edge. Scores for rank skill sat low for all, from near chance to fair. Top signs were family strain, hour caps, a ready CV, self-work thoughts, and school past. One forest method fit best, yet its lead in real forecasts was small. The authors say mixed model sets aid sense-making, but machine learning adds no sharp gain here without more tuning.

Catalog record

CREATORGeorge Bouliotis, M Underwood, R Froud
YEAR2024
COLLECTIONPAPERS
FORMATTXT
FILE SIZE28 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC11606207

Browse the full library · About the Tower of Babel