Using the Power of Predictive Analytics for Case Outcomes ERICSA 52 nd Annual Training Conference & Exposition ▪ April 26 – 30 Hershey Lodge ▪ Hershey, Pennsylvania
Participants Presenter – Edward V. Lehman, Jr. Director, Case Processing & Data Management Philadelphia Family Court – Domestic Relations Division Presenter – Steven J. Golightly, Ph.D. Los Angeles County Child Support Moderator – Joyce Match Business Analyst Manager Pennsylvania Bureau of Child Support Enforcement ERICSA 52 nd Annual Training Conference & Exposition ▪ April 26 – 30 ▪ Hershey Lodge ▪ Hershey, Pennsylvania
Predictive Analytics in Action Edward V. Lehmann, Jr. ERICSA 52 nd Annual Training Conference & Exposition ▪ April 26 – 30 Hershey Lodge ▪ Hershey, Pennsylvania
What is the requirement? Access to the right information is extremely important Determine Next Reduce Increase Effective Work the Appropriate Information Visible Case Worker Right Cases Action Overload Results Management Proactively ERICSA 52 nd Annual Training Conference & Exposition ▪ April 26 – 30 ▪ Hershey Lodge ▪ Hershey, Pennsylvania
Understanding Past, Measuring Present, Predicting the Future ERICSA 52 nd Annual Training Conference & Exposition ▪ April 26 – 30 ▪ Hershey Lodge ▪ Hershey, Pennsylvania
Predictive Analytics in Child Support • Reduce user guesswork and “cherry picking” • Prioritize workload based on high impact Improved • Incorporate historical experience to drive future activities Workforce • Eliminate a one size fits all approach Effectiveness • Efficiency of customer service interactions • Over time reduce future workload • Shift from reactive enforcement to early intervention Increased • Learning component for new case management approaches Resource • Assign high risk cases to case workers sooner Allocation • Different approaches for different regions and different case types Efficiency • Automate certain research processes • Better estimates of delinquencies, child support collections • Fewer child support cases in arrears Improved • Model results can be used to quantify historical process inefficiencies Outcomes • Significant marketing value – “We Know Our Citizens” • More reliable payments for children ERICSA 52 nd Annual Training Conference & Exposition ▪ April 26 – 30 ▪ Hershey Lodge ▪ Hershey, Pennsylvania
Predictive Modeling for Child Support Child support enforcement has traditionally been a reactive process. o What if we had a tool that could help us predict which NCPs are o most likely to become in-arrears in the near future? We could use such a tool to: o Prevent arrears o Decrease custodial parent complaints o Take the right action on a case at the right time o Assign the right case workers to the right cases o Gather information for potential policy changes o Use analytics to make smarter decisions and do more with less . ERICSA 52 nd Annual Training Conference & Exposition ▪ April 26 – 30 ▪ Hershey Lodge ▪ Hershey, Pennsylvania
How do Models Work? Statistical models just refine what we do naturally all the time. For example: which of these NCP’s is most/least likely to pay next month? Tom: Rick: Gene: 28 years old 39 years old 35 years old $100 in arrears $8000 in arrears $2000 in arrears 1 other child on case No other children on case No other children on case Salary attachment No salary attachment No Salary attachment No history of violence No history of violence History of family violence Case is not an NCP has other child support Case is a IV-A assistance assistance case cases ERICSA 52 nd Annual Training Conference & Exposition ▪ April 26 – 30 ▪ Hershey Lodge ▪ Hershey, Pennsylvania
How do Models Work? ERICSA 52 nd Annual Training Conference & Exposition ▪ April 26 – 30 ▪ Hershey Lodge ▪ Hershey, Pennsylvania
Pennsylvania’s Solution Pennsylvania’s Predictive Analytics solution included updates to the existing Performance Improvement Module (PIM) solution and a new application to calculate a predictive analytics “score.” • Allows a worker to calculate a score for a case based on 20 variables • Score is the likelihood of the defendant to pay 80% towards current support obligation in the next three months • Information required to generate the score is easily accessed from the system at the time the support order is created or modified • Provides a list of upcoming child support establishment conferences with the cases assigned to the worker to allow the score creation prior to the conference. ERICSA 52 nd Annual Training Conference & Exposition ▪ April 26 – 30 ▪ Hershey Lodge ▪ Hershey, Pennsylvania
PIM/Predictive Analytics Targeted case lists o Suggested case actions o Predictive score and o reasons Performance metrics o Projects for targeted, o custom outreach including text messages ERICSA 52 nd Annual Training Conference & Exposition ▪ April 26 – 30 ▪ Hershey Lodge ▪ Hershey, Pennsylvania
Payment Score Calculator Objectives • Establish a good • Effective case • Maximize payment pattern: assignment based on performance metrics Increased quantity scores and frequency of • Establishing consistent • Minimize costs payment patterns collections related to based on successful • More effective enforcement business process meetings with actions for various defendants • Improve scores • Make available new cost/effectiveness • Provide the right methods of reaching ratios services at the right out time to encourage • Identifying compliance with the opportunities for order proactive • Let the defendant know enforcement activities the case is being monitored ERICSA 52 nd Annual Training Conference & Exposition ▪ April 26 – 30 ▪ Hershey Lodge ▪ Hershey, Pennsylvania
Variable Selection Final model contains 20 variables 36 variables considered for modeling after Exploratory Data Analysis [EDA] Phase 64 candidate variables created during data scrubbing / brainstorming phase Over 400 data elements collected and considered in variable creation phase The case for which a score is being calculated is compared against the historical behavior of thousands of cases with similar characteristics ERICSA 52 nd Annual Training Conference & Exposition ▪ April 26 – 30 ▪ Hershey Lodge ▪ Hershey, Pennsylvania
Example Predictive Variables Number Predictive Variables 1 Collection Indicator 2 High Number of Enforcement Activities Indicator 3 Number of Cases 4 Number of Enforcement Activities 5 Balance of Arrears 6 Defendant Net Income 7 Active Income Attachment Indicator 8 Number of Defendant Member Addresses on MADD 9 Number of Defendant Employers 10 Distance between the Defendant and Plaintiff These are just a few examples of predictive variables used in Pennsylvania. Variables used in each State are different. ERICSA 52 nd Annual Training Conference & Exposition ▪ April 26 – 30 ▪ Hershey Lodge ▪ Hershey, Pennsylvania
Predictive Modeling Scores Probability of NCP paying 80 percent on current support in the three months after support order issued/modified. 0 – 30% 31 – 50% 80% + 51 – 79% ERICSA 52 nd Annual Training Conference & Exposition ▪ April 26 – 30 ▪ Hershey Lodge ▪ Hershey, Pennsylvania
Confidence in the Score Payment Average Percent of Current Score Support 1 51% 2 66% 3 77% 4 87% To validate the accuracy of the payment score, a study of 5,000 PACSES cases was completed For each payment score, the average FYTD percent of current support collected was calculated. A direct relationship between payment score and percent of current paid was found (i.e., the higher the payment score the higher the percent of current paid. ERICSA 52 nd Annual Training Conference & Exposition ▪ April 26 – 30 ▪ Hershey Lodge ▪ Hershey, Pennsylvania
PSC Enhancements Planned enhancements to the existing functionality of the Payment Score Calculator • Development of a mechanism for calculating a Payment Score for all open cases • Quarterly refresh the Payment Score Calculations on all open cases • Allow worker to complete a guideline calculation if the PSC has been updated within the last three months • Modification of PIM to add several pre-defined filters which use the Payment Score as one of the factors for consideration • Implementation planned for June, 2015 ERICSA 52 nd Annual Training Conference & Exposition ▪ April 26 – 30 ▪ Hershey Lodge ▪ Hershey, Pennsylvania
PIM/Predictive Analytics Effect in Pennsylvania After PIM was implemented, Pennsylvania became the first State to achieve above 80% in both percent of current and percent of arrears PA has been ranked #1 in the United States for both percent of current and percent of arrears, both of which have increased significantly since the implementation of the Performance Improvement Module ERICSA 52 nd Annual Training Conference & Exposition ▪ April 26 – 30 ▪ Hershey Lodge ▪ Hershey, Pennsylvania
Recommend
More recommend
