ANCHOR

Explainability Transparency

Description

ANCHOR generates high-precision if-then rules that explain individual predictions by identifying the minimal set of feature conditions that guarantee a specific prediction with high confidence. It searches for 'anchor' conditions (e.g., 'age > 30 AND income < £50k') that ensure the model gives the same prediction at least 95% of the time when those conditions are met. This creates human-readable rules that users can trust as sufficient conditions for understanding why a particular decision was made.

Example Use Cases

Explainability

Explaining loan application decisions with rules like 'IF credit_score > 650 AND debt_ratio < 0.4 THEN approval = 95% likely', giving applicants clear, actionable conditions they can understand and potentially improve.

Generating diagnostic rules for medical predictions such as 'IF fever > 38.5°C AND white_blood_cells > 12,000 THEN infection = 92% likely', helping clinicians validate automated diagnoses with trusted clinical indicators.

Transparency

Creating transparent hiring decisions with rules like 'IF experience >= 3_years AND degree = relevant THEN hire = 89% likely', providing clear justification for recruitment decisions that can be audited for fairness.

Limitations

Limited to local explanations for individual instances, cannot provide global insights about overall model behaviour.
Requires discretisation of continuous features, which can lose important nuanced information and create arbitrary thresholds.
May fail to find suitable anchor rules if precision requirements are too strict or if the prediction space is highly complex.
Computationally expensive as it requires extensive sampling to validate rule precision, especially for high-dimensional data.

Resources

Anchors: High-Precision Model-Agnostic Explanations

Research Paper•Marco Tulio Ribeiro, Sameer Singh, and Carlos Guestrin•Jan 1, 2018

marcotcr/anchor

Software Package

alibi/alibi

Software Package

Interpretable Machine Learning - Anchors

Documentation

Related Techniques

Name	Description	Assurance Goals
Contextual Decomposition	Contextual Decomposition explains LSTM and RNN predictions by decomposing the final hidden state into contributions from individual inputs and their interactions. Unlike simpler attribution methods, it separates the direct contribution of specific words or phrases from the contextual effects of surrounding words. This is particularly useful for understanding how sequential models process language, as it can identify whether a word's influence comes from its individual meaning or from its interaction with nearby words in the sequence.	Explainability Transparency
Principal Component Analysis	Principal Component Analysis transforms high-dimensional data into a lower-dimensional representation by finding the directions (principal components) that capture the maximum variance in the data. Each component is a linear combination of original features, with the first component explaining the most variance, the second component the most remaining variance orthogonal to the first, and so on. This technique reveals underlying patterns in data structure, enables visualization of complex datasets, and helps identify which combinations of features drive the most variation in the data.	Explainability
Area Under Precision-Recall Curve	Area Under Precision-Recall Curve (AUPRC) measures model performance by plotting precision (the proportion of positive predictions that are correct) against recall (the proportion of actual positives that are correctly identified) at various classification thresholds, then calculating the area under the resulting curve. Unlike accuracy or AUC-ROC, AUPRC is particularly valuable for imbalanced datasets where the minority class is of primary interest---a perfect score is 1.0, whilst random performance equals the positive class proportion. By focusing on the precision-recall trade-off, it provides a more informative assessment than overall accuracy for scenarios where false positives and false negatives have different costs, especially when positive examples are rare.	Reliability Transparency Fairness
Jackknife Resampling	Jackknife resampling (also called leave-one-out resampling) assesses model stability and uncertainty by systematically removing one data point at a time and retraining the model on the remaining data. Unlike bootstrapping which samples with replacement, jackknife creates n different models by excluding each of the n data points once. This systematic approach reveals how individual points influence results, provides robust estimates of prediction variance, and identifies unusually influential observations that may be outliers or leverage points affecting model reliability.	Reliability Transparency Fairness
Sobol Indices	Sobol Indices quantify how much each input feature contributes to the total variance in a model's predictions through global sensitivity analysis. The technique calculates first-order indices (individual feature contributions) and total-order indices (including all interaction effects involving that feature). By systematically sampling the input space and decomposing output variance, Sobol Indices reveal which features drive model uncertainty and which interactions between features are most important for predictions.	Explainability Fairness
Fair Adversarial Networks	An in-processing fairness technique that employs adversarial training with dual neural networks to learn fair representations. The method consists of a predictor network that learns the main task whilst an adversarial discriminator network simultaneously attempts to predict sensitive attributes from the predictor's hidden representations. Through this adversarial min-max game, the predictor is incentivised to learn features that are informative for the task but statistically independent of protected attributes, effectively removing bias at the representation level in deep learning models.	Fairness Transparency Reliability

Tags

Applicable Models:

Data Requirements:

No Special Requirements

Data Type:

Evidence Type:

Quantitative Metric

Expertise Needed:

Explanatory Scope:

Lifecycle Stage:

Model Development

Technique Type: