Email Intent Classifier Confusion Matrix

An email-intent classifier sends customer messages to Order, Return, Shipping or Account queues. The matrix shows correct assignments on its diagonal and the cross-queue errors around it. For example, Return messages sent to Order may indicate ambiguous wording or an unclear intent definition. This view helps an automation team decide where human review remains necessary. It should be refreshed after policy changes or new product launches because the language customers use can change. The values are counts, not percentages, so reviewers should also consider the total volume for each row before declaring one class better than another.

類型熱圖引擎 echarts-heatmap更新時間 2026/9/24

需求

“Create a confusion matrix heatmap for an email-intent classifier with actual rows and predicted columns Order, Return, Shipping and Account. Use counts by actual row: Order 91, 7, 3, 2; Return 9, 76, 5, 4; Shipping 2, 6, 84, 7; Account 3, 2, 8, 79.”

接著試試Change the Account predicted Shipping count to 5.Remove the visual scale from the chart.

這張圖裡有什麼

看懂背後的決策。

01Use customer intents

Align classes with real queues.

02Review related intents

Order and Return errors may need new examples.

03Track validation date

Compare the same test protocol over time.

Use when one incoming email has one agreed routing intent.

瀏覽所有熱圖範本 →

常見問題

Why include four intents?

It reflects distinct queues in a common support-routing workflow.

What does an off-diagonal count mean?

It is a message routed to a different intent from its actual label.

Should this run without review?

That depends on the impact of each routing error and the team's controls.