Phase 3: Explainability & Transparency · 40 min · Python · LIME · scikit-learn

LIME — Local Interpretable Model-Agnostic Explanations

SHAP explains with game theory. LIME explains with a local surrogate.

Hiring signal: LIME appears alongside SHAP in most RAI postings. Being able to compare LIME and SHAP explanations on the same prediction — and explain when they differ — shows depth in explainability tooling.

What you will learn

Explain LIME's local surrogate model approach
Generate LIME explanations for individual predictions
Compare LIME and SHAP explanations on the same predictions
Articulate LIME's limitations: instability and sampling sensitivity

The Problem

SHAP is powerful but can be slow for non-tree models (KernelExplainer) and sometimes produces explanations that are hard to explain to non-technical stakeholders. LIME offers an alternative approach: instead of computing exact Shapley values, it fits a simple, interpretable model (like a linear regression) locally around the prediction being explained.

How LIME Works

Take the instance you want to explain
Generate perturbed samples around it (slightly modified versions)
Get the model's predictions for all perturbed samples
Weight the samples by proximity to the original instance
Fit a simple linear model on the weighted samples
The linear model's coefficients are the explanation

The result is a set of feature weights that show how each feature contributed to this specific prediction — similar to SHAP's local explanation but using a different mathematical approach.

Unlock the full lesson

You've read the first 2 sections. The rest of this lesson covers SHAP vs. LIME: When They Differ, Building the LIME Module, What's Next — plus a hands-on lab, quiz, and project artifact.

Create a free account to unlock Phase 0 and Phase 1 of every course — no credit card.