Feature extraction approach in TensorFlow - Model Metrics & Evaluation

Metrics & Evaluation - Feature extraction approach

Which metric matters for Feature Extraction and WHY

Feature extraction helps turn raw data into useful information for a model. The key metrics to check are model accuracy, precision, and recall after using extracted features. These metrics show if the features help the model make better predictions.

Accuracy tells how often the model is right overall. Precision shows how many predicted positives are truly positive. Recall shows how many actual positives the model finds. Good features improve these numbers.

Confusion Matrix Example

      Actual \ Predicted | Positive | Negative
      -------------------|----------|---------
      Positive           |    TP=80 |   FN=20
      Negative           |    FP=10 |   TN=90
    

From this matrix:

• Precision = 80 / (80 + 10) = 0.89
• Recall = 80 / (80 + 20) = 0.80
• Accuracy = (80 + 90) / 200 = 0.85

This shows how well the features help the model separate classes.

Precision vs Recall Tradeoff with Feature Extraction

Feature extraction can affect precision and recall differently. For example:

• If features miss important details, recall drops (model misses positives).
• If features add noise, precision drops (model predicts too many false positives).

Example: In medical diagnosis, high recall is critical to catch all sick patients, even if precision is lower. In spam detection, high precision is important to avoid marking good emails as spam.

Good vs Bad Metric Values for Feature Extraction

Good: Accuracy > 80%, Precision and Recall both above 75%. This means features help the model find and correctly identify important patterns.

Bad: Accuracy around 50-60%, Precision or Recall very low (below 50%). This means features are not informative or add noise, hurting model performance.

Common Pitfalls in Feature Extraction Metrics

• Accuracy paradox: High accuracy but poor recall or precision can mislead about feature quality.
• Data leakage: Features accidentally include future or target info, inflating metrics falsely.
• Overfitting: Features too specific to training data cause high training metrics but poor test results.
• Ignoring class imbalance: Metrics like accuracy can be misleading if classes are uneven.

Self Check

Your model uses extracted features and shows 98% accuracy but only 12% recall on fraud cases. Is it good?

Answer: No. The low recall means the model misses most fraud cases, which is critical to detect. Despite high accuracy, the features do not help find fraud well. You should improve feature extraction to increase recall.

Key Result

Feature extraction quality is best judged by balanced precision and recall improvements, not just accuracy.