Account Receivable Collection is probably one of the most data-intensive fields. Collection Agents handle data along the way of managing their Debt portfolio.
It starts by the Data Cleaning and Enrichment Process: where the missing and erroneous data are wrangled and transformed, then enriched with important contact data such as Debtors Emails, phone numbers and Addresses formatted to the local Postcode standard.
The second Data-Driven Process is Portfolio Analytics, where Portfolio managers operate Portfolio Segmentation, where the main aim is to split the Debts portfolio to various coherent buckets using multiple criteria such as Receivable Aging, Debt balance, Credit Bureau Score, Location, Purchased products, etc..
In addition to the rule-based Segmentation described below, Debt Collection Analysts might use Machine Learning techniques to learn from historical Debtors behaviour regarding the collections actions. This Learning will help to build a Debt Collection Scoring describing the probability of recovery of the debt and even recommending the best actions and timing to undertake for maximising the Recovery likelihood.
The last, and not least, Data-Driven Process to take into consideration is Key Performance Indicators (KPI's) Tracking. Data Analytics can help managers to analyse collection logs and produce pertinent KPI's describing the efficiency of the collection process, from Data Cleaning and Enrichment, Generating Promises, Keeping Promises, to Payments. The most important KPI's to track are the following :
- Percentage of Accounts with Missing or Incomplete Data
- Percentage of Accounts Requiring Skip tracing
- Average Age of Purchased Debt
- Right Party Contact (RPC) Rate
- Percentage of Outbound Calls Resulting in Promise to Pay
- Percentage of Promises to Pay Kept
- Days Sales Outstanding (DSO)
- Collection Effectiveness Index (CEI)
- Collections Revenue per Collections Agent