Child Support Case Management Predictive Analytics

Maximize Collection For Child Support From NCP

Objective

  • Payments are ranked on a scale of 1 (full payment) to 5 (no payment). The project objective is to predict the collection category of cases in future monthsbased on its past payment pattern and various attributes

Solution

  • The project involved the analysis of a large number of cases (over 300,000 per month for one state) and of over 130 variables. Multinomial logit models were used to predict payment category.

Background

  • The project was implemented for 4 major US states. There are two parents in every child support case. One is the Custodial Parent (CP) – the parent who lives with the child the majority of the time and has the primary day-to-day responsibility; the other is the Non-Custodial Parent (NCP) who also has important responsibilities. An aggrieved CP may appeal to the state to enforce child support by the NCP.

Benefit

  • Early warning of cases where payment levels are likely to deteriorate enabling case workers to take corrective action
  • Detection of cases where the NCP has the capability to pay more than he does so that the court may be moved to increase the child support amount
Sr.No Month Correct Classification
1 Feb-13 83%
2 Mar-13 77%
3 Apr-13 77%
4 May-13 71%
5 Jun-13 80%
6 Jul-13 74%

Download Case Study

    Share This Case Study