AI Drives Collection Revolution- Decisimo

Published on: 2024-08-10 18:35:48

Debt collection specialists in the analytical field play a vital role in predicting the likelihood of recovery and optimizing collection strategies. One useful tool for achieving this is a collections scorecard. In this article, we will outline how to build a comprehensive collections scorecard that accurately predicts the probability of recovery.

I. Variables and Data Types

A. Collection Behavior Data

  1. Number of phone calls made in the last 1, 2, and 3 periods
  2. Total number of phone calls made
  3. Number of phone calls connected in the last 1, 2, and 3 periods
  4. Total number of phone calls connected
  5. Connection rate for the last 1, 2, and 3 periods
  6. Pverall phone connection rate
  7. Number of days lost contact in the last 1, 2, and 3 periods
  8. Total days lost contact
  9. Number of valid friends
  10. Number of valid contacts
  11. Average call duration per call
  12. Total call duration
  13. Total number of call backs
  14. Total collection messages sent
  15. Total number of collectors involved
  16. Total number of collection letters sent

B. Customer Personal Information

  1. Age
  2. Gender
  3. Occupation
  4. Education
  5. Monthly income
  6. Marital status
  7. Housing situation
Decisimo decision engine

Try our decision engine.

Related Articles

  • Portfolio management in lending: what matters most

    Portfolio management in a lending company is not just monitoring arrears. It is the operating layer that connects credit policy, collections, capital planning, and funding decisions. The goal is simple: understand how the portfolio behaves, where it is changing, and what action the data requires.

  • Antifraud articles

    This collection maps the core techniques, signals, and control points behind antifraud work. It covers device and browser fingerprinting, IP and email checks, rule engines, case management, and detection patterns for account takeover, synthetic identity fraud, merchant fraud, and bot activity.

  • The Fallacy of Evading Fingerprinting by Disabling JavaScript

    Disabling JavaScript does not stop fingerprinting. This article explains why that assumption fails, how no-JS fingerprinting works, and which browser signals still expose identifying data through normal HTTP requests.

  • Decision tables: practical guide

    Decision tables are compact matrices that express decision logic more clearly than large decision trees. They make rules easier to read, test, and audit. This guide explains how to design solid tables, make conditions and outcomes mutually exclusive and collectively exhaustive, order them by precedence, use a catch-all row, and test boundary, standard, and error paths.

  • Why segmented pre-collection activity matters for lending businesses

    Segmented pre-collection helps lending businesses focus on accounts that need attention before they become delinquent. This article explains what pre-collection is, why segmentation matters, and the main ways lenders can use it to improve recovery without unnecessary contact with borrowers who are likely to pay on time.