From Prediction to Assignment: Capacity-Constrained Agent–Case Allocation in Large-Scale Debt Collection

Post-default debt collection requires agencies to allocate delinquent cases across collectors under eligibility and workload constraints, yet most predictive research concentrates on credit scoring rather than on the assignment decision itself. This paper develops a prediction-to-assignment framework using 1.28 million longitudinal assignment episodes from utilities portfolios managed by a large European credit management company. A model selected on development data scores the feasible alternative agents at each historical decision point, reconstructed under strict temporal ordering. The resulting probabilities are used to evaluate capacity-constrained assignment policies, and the predicted differences between agents are tested against observed outcomes. Under the model’s scores, a conservative policy that prohibits score-decreasing reassignments raises mean predicted recovery probability by 2.37 percentage points under historical workloads. An observational contrast calibration, however, indicates that outcomes reflect the predicted agent differences at about 40% of their strength (slope 0.41); after calibration, the conservative policy gain is 0.96 points (95% period-bootstrap interval 0.89–1.03), 0.60–1.32 across the slope’s confidence interval, and 0.53 when combining the natural-roster slope, daily batches, and unchanged assignments outside the candidate rules. Doubly robust estimates for simpler policies imply slopes of 0.28–0.42, and random feasible reassignment yields negligible gain. Model-guided agent–case matching therefore retains positive estimated value under operational constraints, but uncalibrated scores substantially overstate it.