Bias detection and mitigation in ML Python - Model Pipeline Trace

Model Pipeline - Bias detection and mitigation

This pipeline shows how we detect bias in data and reduce it to make fairer predictions. We start with raw data, check for bias, adjust the data or model, train the model, and then check if bias is reduced.

Data Flow - 6 Stages

1Raw Data Collection

1000 rows x 6 columns→Collect data including features and sensitive attribute (e.g., gender)→1000 rows x 6 columns

Rows with features like age, income, education, gender, and target label

↓

2Bias Detection

1000 rows x 6 columns→Calculate bias metrics like demographic parity difference→Bias score: 0.25 (indicating bias)

Demographic parity difference = 0.25 means groups show disparity

↓

3Bias Mitigation - Reweighing

1000 rows x 6 columns→Assign weights to samples to balance groups→1000 rows x 6 columns with weights

Samples from underrepresented group get higher weights

↓

4Train/Test Split

1000 rows x 6 columns with weights→Split data into training (80%) and testing (20%) sets→Training: 800 rows x 6 columns with weights, Testing: 200 rows x 6 columns without weights

Training set has 800 samples with weights

↓

5Model Training

800 rows x 6 columns with weights→Train weighted logistic regression model→Trained model

Model learns to predict target with bias mitigation

↓

6Evaluation

200 rows x 6 columns→Calculate accuracy and bias metrics on test set→Accuracy: 0.82, Bias score: 0.05

Bias score reduced from 0.25 to 0.05 after mitigation

Training Trace - Epoch by Epoch

Loss
0.7 |****
0.6 |****
0.5 |****
0.4 |****
0.3 |****
    +------------
     1 2 3 4 5 Epochs

Epoch	Loss ↓	Accuracy ↑	Observation
1	0.65	0.60	Initial training with high loss and low accuracy
2	0.50	0.70	Loss decreased, accuracy improved
3	0.40	0.75	Model learning patterns, bias mitigation helping
4	0.35	0.80	Loss continues to decrease, accuracy rising
5	0.30	0.82	Training converging with good accuracy and lower bias

Prediction Trace - 6 Layers

Layer 1: Input Sample

Layer 2: Feature Encoding

Layer 3: Model Input

Layer 4: Logistic Regression Model

Layer 5: Sigmoid Activation

Layer 6: Final Prediction

Model Quiz - 3 Questions

What does a bias score of 0.25 before mitigation indicate?

A The model accuracy is 25%

B The model has perfect fairness

C The model favors one group over another

D The data has no sensitive attributes

Key Insight

Detecting bias early and applying mitigation like reweighing helps train fairer models without sacrificing accuracy. Monitoring bias metrics alongside accuracy ensures balanced predictions.