Based on data from two regions in Ireland, identifies the probability that a new entrant to unemployment will become a long-term unemployed. Considers their education and training, the way they are looking for work, the distribution of unemployment durations, etc.
Statistical models can help public employment services to identify factors associated with long-term unemployment and to identify at-risk groups. Such profiling models will likely become more prominent as increasing availability of big data combined with new machine learning techniques improve their predictive power. However, to achieve the best results, a continuous dialogue between data analysts, policymakers, and case workers is key. Indeed, when developing and implementing such tools, normative decisions are required. Profiling practices can misclassify many individuals, and they can reinforce but also prevent existing patterns of discrimination.
Based on a survey of state administrators in the United States who have implemented the Workers Profiling and Reemployment Service System (WPRS) and of claimant-level data from the prototype system, evaluates the impact of the system on identifying unemployment insurance (UI) claimants who are likely to exhaust their UI benefits and will need re-employment services to make the transition to new employment.
Contains national reports from Australia; Canada; United Kingdom & United States on identification of jobseekers at risk of becoming long-term unemployed (profiling) prepared as background material to the meeting of the OECD Employment, Labour and Social Affairs Committee held in Paris in October 1997