Invoice Fraud Screening Confusion Matrix

This binary matrix separates invoices that were actually clear from those identified as fraud after review. A fraud invoice predicted clear is a false negative, while a clear invoice sent to review is a false positive. Both matter, but their business costs are different. The chart gives analysts a shared view of that trade-off before they adjust a model threshold or change review capacity. It does not establish an acceptable error rate on its own. That decision requires fraud-loss estimates, analyst capacity and governance. Use a fixed evaluation period and documented ground truth when comparing successive models.

類型熱圖引擎 echarts-heatmap更新時間 2026/9/24

需求

“Create a binary confusion matrix heatmap for invoice fraud screening with actual rows Clear and Fraud and predicted columns Clear and Review. Use counts: actual Clear predicted Clear 890 and Review 74; actual Fraud predicted Clear 9 and Review 27.”

接著試試Change the fraud predicted Clear count to 6.Rename Review to Manual review.

這張圖裡有什麼

看懂背後的決策。

01Identify false clears

Missed fraud can carry high risk.

02Identify false reviews

Extra reviews consume analyst time.

03Keep labels precise

Review is not the same as confirmed fraud.

Use for threshold discussion with a documented labeling process.

瀏覽所有熱圖範本 →

常見問題

What is a false negative here?

An actual fraud invoice predicted as Clear.

What is a false positive?

A clear invoice sent to Review.

Can a threshold change the matrix?

Yes. A stricter or looser threshold changes the balance of these errors.