Vishwas
Explain Prediction
Generate human-readable explanations for model predictions
POST
Request
Unique identifier for your model.
The input features for the prediction to explain.
The model’s prediction (probability or class label).
Explanation method to use:
shap- SHAP values (recommended)lime- LIME explanationsanchors- Rule-based anchorscounterfactual- Counterfactual examplesprototype- Similar training examples
Number of top features to include in explanation.
Language for human-readable text. Supports:
en, hi, ta, te, bn, mr, gu, kn, ml, pa, or, as.Target audience for explanation:
technical- For data scientists and ML engineersbusiness- For business stakeholderscustomer- For end users/customers
Response
Unique explanation identifier.
The model ID.
The explanation method used.
The prediction being explained.
Feature contributions ranked by importance.
Human-readable explanation text.
Counterfactual examples (if method is
counterfactual).
