{% block content %}

Overview

This overview provides a high-level assessment of the model's resilience to distribution shifts between baseline and target distributions.

{% include "report_types/resilience/components/summary/summary_overview.html" %}

Performance Gap Analysis

{% include "report_types/resilience/components/charts/performance_gap_chart.html" %}

Performance gap chart data will display here.

Distribution Shift Analysis

{% include "report_types/resilience/components/charts/distribution_chart.html" %}

Distribution shift chart data will display here.

Feature Impact Analysis

{% include "report_types/resilience/components/charts/intensity_chart.html" %}

Feature impact chart data will display here.

Key Insights

Performance Impact
📉
{% if performance_gap is defined %}

The model experiences a {% if performance_gap > 0.2 %}significant{% elif performance_gap > 0.1 %}moderate{% else %}minor{% endif %} impact when exposed to distribution shifts, with an average performance gap of {{ (performance_gap * 100)|round(1) }}%.

Average Gap:
{{ (performance_gap * 100)|round(1) }}%
{% else %}

Information about model performance impact is not available from test results.

Average Gap:
Data not available
{% endif %}
Distribution Shift
🔄
{% if avg_dist_shift is defined %}

The dataset exhibits {% if avg_dist_shift > 0.5 %}significant{% elif avg_dist_shift > 0.2 %}moderate{% else %}minor{% endif %} distribution shifts, with an average distance metric of {{ avg_dist_shift|round(2) }}.

Shift Magnitude:
{{ avg_dist_shift|round(2) }}
{% else %}

Information about distribution shift magnitude is not available from test results.

Shift Magnitude:
Data not available
{% endif %}
Sensitive Features
⚠️

{% if sensitive_features|length > 0 %}{{ sensitive_features|length }} features show high sensitivity to distribution shifts, with the greatest impact observed in the most affected features.{% else %}No high sensitivity features were identified in the analysis.{% endif %}

Scenario Analysis
🔍

{% if shift_scenarios|length > 0 %}{{ shift_scenarios|length }} different shift scenarios were analyzed to evaluate the model's resilience under various conditions.{% else %}No shift scenarios were available for analysis.{% endif %}

Shift Results

{% include "report_types/resilience/components/tables/shift_results_table.html" %}
{% include "report_types/resilience/components/tables/feature_impact_table.html" %}

Resilience Recommendations

{% if resilience_score is defined and resilience_score is not none and resilience_score < 0.7 %}
🔍

Investigate Feature Distributions

High

Analyze the distribution patterns of the most sensitive features to understand sources of instability.

Review the Distribution Analysis tab for detailed insights
{% endif %} {% if performance_gap is defined and performance_gap is not none and performance_gap > 0.15 %}
⚖️

Balance Training Data

High

Enhance training data with examples from underrepresented regions to improve model performance under distribution shifts.

{% endif %}
🔄

Regular Monitoring

Medium

Set up ongoing monitoring of feature distributions in production to detect shifts early.

{% if avg_dist_shift is defined and avg_dist_shift is not none and avg_dist_shift > 0.3 %}
🛡️

Implement Robust Features

Medium

Consider feature engineering techniques that are more robust to distribution changes.

{% endif %}
{% endblock content %}