Collections Predictor

Learning objectives

• Explain the main treasury decision that Collections Predictor is designed to support.
• Use Collection strategy, Enable AI recommendation to test how different assumptions change the scenario.
• Interpret Output Summary in plain language and connect them to an action or conclusion.
• State one limitation, risk, or governance consideration before using the result in a real decision.

Run modes

• Supported modes: Browser
• Demo type: Interactive browser demo
• Primary launch surface: index.html

Before you start

Starts immediately in browser with no installs, no API keys, and classroom-safe defaults.

This helps set classroom expectations before students click into the live experience.

Core context

Look for customer risk score, payment history, amount due, and collection priority.

Observe how segmenting customers changes collection strategy.

Concepts covered

What students should note

Note that collections analytics should improve cash recovery while preserving customer relationships.

List of steps

• Choose the run mode that fits the class: Browser.
• Review the default assumptions before changing anything.
• Change one or two inputs, then use `Reset Scenario`.
• Read Output Summary first, then compare any supporting metrics, charts, or AI text.
• Capture one insight, one limitation, and one action recommendation.

Input variables explained

• `Collection strategy` changes one part of the scenario; increase or decrease it deliberately and watch how the output shifts.
• `Enable AI recommendation` changes one part of the scenario; increase or decrease it deliberately and watch how the output shifts.

Decision buttons explained

• `Reset Scenario` restores the default collections case so learners can compare strategies from a known baseline.
• `Export Result` saves the current collections recommendation and projected outcome for class discussion or follow-up analysis.

Outputs explained

• Read the predicted collection outcome and recommended treatment path together, because the suggested action matters as much as the score.
• Look for recovery potential, urgency, and customer treatment differences across strategies or segments.

What to notice

• Look for customer risk score, payment history, amount due, and collection priority
• Observe how segmenting customers changes collection strategy
• Note that collections analytics should improve cash recovery while preserving customer relationships
• Compare the headline output with supporting views such as Output Summary before drawing a conclusion

Discussion and reflection

• What business or technical decision would you make differently after using Collections Predictor?
• If you changed one assumption and ran `Reset Scenario`, which output moved the most and why?
• What would you still want to validate with real data, policy, or expert review before acting on the result?