Analysis of Unemployment Data and Intervention Instruments

Abstract

It is important to analyse unemployment data, so intervention instruments can be improved and the unemployed can exit social security faster. To this end this paper presents a number of data analysis techniques that can be used to estimate the probability of outflow and the effectiveness of intervention instruments.

Firstly classification trees and survival analysis are used to give insight into the influence of features on the chance of outflow. Furthermore the classification trees can also be used to predict the chance of outflow for new clients. We found some features that seem to greatly influence the chance of outflow.

Secondly novel matching algorithms are used to create a treatment and comparable control group for four intervention instruments. Survival analysis is then used to analyse the differences between the groups. We conclude that two of the four intervention instruments are significantly better than other intervention instruments.