Recall in Machine Learning

 

🔁 Recall in Machine Learning

Recall measures a model’s ability to find all the relevant (positive) instances in a dataset.

---

📌 Definition

$$\text{Recall} = \frac{\text{True Positives (TP)}}{\text{True Positives (TP)} + \text{False Negatives (FN)}}$$

---

🔍 Interpretation

"Out of all actual positive cases, how many did the model correctly identify?"

---

✅ Example (Disease Detection):

If 100 people actually have a disease, and the model identifies 85 of them:

$$\text{Recall} = \frac{85}{100} = 0.85 \text{ or } 85\%$$

---

📉 When High Recall Matters

Use recall when missing a positive instance is more serious than a false alarm:

• Medical diagnosis

• Search engines

• Fraud detection

---

⚠️ Trade-off

High recall can come at the cost of low precision—you may catch more positives, but with more false positives too.