Experian DataLabs onsite – machine-learning deep-dive

Explain how PCA achieves dimensionality reduction and why L2-normalization beforehand can matter.

Derive the logistic-regression gradient via back-propagation.

When would you move the classification threshold to improve FPR or TPR?

What baseline models did you compare against and why did you finally choose logistic regression?

Define knowledge-informed machine learning and give an example.

Discuss eigenvectors/variance, maximum-likelihood gradients, ROC curves, model-selection criteria, domain priors.

Experian Data Scientist interview question: Explain PCA Dimensionality Reduction and L2-Normalization Importance. {"blocks": [{"key": "a5817426", "text": "Scenario", "type": "header-two", "depth": 0, "inlineStyleRanges": [], "entityRanges": [], "data": {...