Since 2012, Ireland's DSP has used a statistical model, PEX, to flag jobseekers at risk of long-term unemployment; a 2019 evaluation found 20% of claimants had no PEX score at all. The model was recalibrated in 2022 and remains in use today.
20 %
Claimants with no PEX score (2013)
8 characteristics (approx.)
Characteristics used in the scoring model (since 2012)
18 months
Outcome tracking window for the training cohort (2006 cohort)
Details
Maturity
Established
Promoter
Department of Social Protection (Intreo), with the Economic and Social Research Institute (ESRI)
Period
Model built on 2006 cohort data; operationalised as PEX from 2012; revised 2014; recalibrated 2022; in active use as of 2024
Keywords
public employment services, labour market activation, welfare caseload targeting, statistical profiling
Context
Ireland's Department of Social Protection has operated the PEX (Probability of Exit) statistical profiling tool since 2012 within its Intreo employment-office network, predicting a jobseeker's risk of remaining unemployed after 12 months in order to target activation support.
Activities
PEX uses probit regression trained on a 2006 jobseeker cohort followed for 18 months, scoring around eight characteristics — age, education, literacy, recent unemployment history, transport access and others — with lower scores indicating higher long-term unemployment risk and triggering more intensive case-officer engagement. The model was revised in 2014 and recalibrated in 2022 using updated administrative data.
Results
A 2019 evaluation found a significant implementation gap: 20% of individuals in Intreo offices in 2013 had no PEX score at all, and others lacked complete profiling-questionnaire responses. Despite this shortfall, the Department continued and recalibrated the model, with active deployment continuing as of 2024.
Implementation
Indicative cost
Low (< €50k)
Time to results
Long (> 3 years)
Staffing & skills
Department of Social Protection (Intreo) operates the model and case-officer engagement, ESRI conducts independent evaluation and recalibration research
Conditions for success
Complete profiling-questionnaire data collection at point of registration
Periodic recalibration using updated administrative data (as done in 2022)
Common failure modes
Substantial implementation gap — 20% of claimants lacked a PEX score in 2013 due to incomplete data collection/questionnaire completion, undermining targeting
Where it fits
Governance type
national public employment service
Scale
national
Income level
high-income
Do you run this practice?
Claim it —
verified implementers get a public contact pathway and can propose corrections.
Data sources
Where this practice's information was retrieved from, and when.
