What is predictive pairing in debt collection?

Where it comes from

Contact centers have been answering "who takes this one?" for fifty years, and each answer used a little more information.

• 1970s: the next free agent. Automatic call distributors sent each call to the agent who had been idle longest. Simple and fair, but blind to who is good at what.
• 1990s: skills routing. Calls went to a group with the right skill: a language, a product, a balance band. That is still the right first cut, and most floors use it today.
• From the mid-2000s: predictive pairing in the enterprise. Afiniti, based in Washington, D.C., built predictive pairing for the largest contact centers in the world, mostly inbound: telecoms, insurers and banks with thousands of agents. Its results were measured against control groups, which showed the idea works at scale.
• Since 2011: predictive pairing on outbound floors. The team behind BestPair has matched outbound agents to leads and accounts since 2011, on insurance, banking and collection campaigns, always measured against a control group.
• Now: US collection floors. Collection floors dial out, work agent-owned lists and are measured in dollars collected. BestPair brings predictive pairing to them as a dialer mode.

The theory behind it

• Comparative advantage. Every collector is stronger with some kinds of accounts than others. One leaderboard hides that; splitting results by type of account shows it. Why collectors convert differently.
• The pair is what matters. When the result depends on the match, sorting well beats ranking.
• Assignment. With a prediction for every collector and every account, picking the best set of pairs within each collector’s capacity is a classic problem with a known solution, Harold Kuhn’s Hungarian method from 1955. That is why the best collectors do not simply get everything.
• Measured, not assumed. A prediction can be wrong, so the result is checked against a control group of accounts assigned the usual way over the same weeks.

When it works

• History tied to collectors. Calls and payments linked to the collector who worked them, ideally 24 months. No consumer names or contact details.
• A choice of collector. Agent-owned lists or agent queues on a preview or manual dialer, segments in the skills-based router on a predictive dialer, a mix on a progressive or power dialer. A purely inbound floor that sends each call to the next free agent leaves nothing to choose.
• Enough collectors. Usually 25 or more, so each kind of account has enough collectors and history to tell skill from luck.
• Collectors who differ. If they do about the same on the same kinds of accounts, there is nothing to match. Often nobody knows until the data is read.
• Account details at assignment time. Balance, age of debt, placement date, state and similar fields on every account. Which details matter.

Where it pays most

• Low conversion. When most right-party contacts do not pay or promise, the conversation decides the outcome, and who has it matters most. What RPC conversion is.
• Persuasion-heavy calls, where the collector changes the result.
• Many similar decisions every day, which give both the choice and the history.
• Outcomes that show quickly, so results can be measured and the predictions rebuilt.