What this demo is about
Prioritizing overdue receivables requires balancing recovery speed, customer relationship risk, and analyst effort.
Treasury Analytics • Browser Mode • 10-15 min
Collections Predictor
Students can test how different collections strategies change recovery expectations, model confidence, and next-best-action guidance without any external service.
Runs fully in browser
Scenario-based
Optional AI explanation
Learning objectives
- Compare baseline, improved, and aggressive collection strategies.
- Interpret recovery rate and prediction accuracy together.
- Translate analytics into a concrete collection action.
How to use the demo
Step 1
Select a collections strategy and decide whether to show AI guidance.
Step 2
Review the receivables summary and inspect the highest-risk invoices.
Step 3
Use the recommended action to explain which customers should be contacted first and why.
Input Variables
Strategy changes the expected recovery and model accuracy. AI guidance adds a plain-language recommendation layer on top of the same scenario math.
Decision Buttons
Reset Scenario returns the demo to the default baseline. Export Result downloads the current scenario snapshot for discussion or grading.
Output Summary
Total accounts receivable
$45.2M
Predicted recovery
$39.3M
Model accuracy
87%
Invoice Queue
| Invoice | Customer | Amount | Days overdue | Collection probability | Risk |
|---|---|---|---|---|---|
| INV-2024-001256 | City Council | $2.4M | 94 | Critical | |
| INV-2024-001198 | Global Solutions | $1.1M | 73 | High | |
| INV-2024-001305 | Metro Retail | $640K | 38 | Low |
AI Recommendation
Focus on INV-2024-001256 and INV-2024-001198 first.
Most likely interpretation: higher-recovery strategies increase expected cash collection, but can reduce customer goodwill or confidence if pushed too aggressively.