Measurement strictness settings provide fine-grained control over how SmartSize AI Fit Recommender’s recommendation algorithm matches customer measurements to your size ranges, allowing you to optimize fit accuracy for different garment types.

Understanding Strictness Levels

The Four Strictness Modes

SmartSize AI Fit Recommender offers four distinct strictness levels, each with specific matching behavior:

1. Flexible (Default)

Algorithm Behavior: Uses sophisticated scoring to find the best overall fit, allowing slight variations for optimal recommendations.

When It Applies:

  • Customer measurements slightly outside ranges can still get recommendations
  • Algorithm weighs multiple factors including measurement proximity and size likelihood
  • Provides the most recommendations with balanced fit optimization

Best For:

  • General clothing and everyday wear
  • Items where comfort is prioritized over precise fit
  • Situations where you want maximum recommendation coverage
  • Most standard garment categories (Top, Bottom, Both)

2. Must Be Inside Range

Algorithm Behavior: Customer measurements must fall exactly within the defined size range for that measurement.

When It Applies:

  • Eliminates sizes where customer measurements fall outside the measurement range
  • Strict boundary enforcement with no tolerance for oversizing or undersizing
  • Only recommends sizes where all enabled measurements are within range

Best For:

  • Formal wear and tailored clothing
  • Items with precise fit requirements (uniforms, professional attire)
  • Garments where proper fit is critical for function or appearance
  • High-end products where customers expect perfect fit

3. In Range or Bigger

Algorithm Behavior: Allows customer measurements that are within range OR larger than the maximum range.

When It Applies:

  • Accepts measurements at or above the size range
  • Prevents recommending sizes that would be too small
  • Allows for loose-fitting preferences and layering needs

Best For:

  • Outerwear and jackets (layering accommodation)
  • Loose-fit and oversized styles
  • Comfort-focused garments
  • Items where being too tight is worse than being too loose

4. In Range or Smaller

Algorithm Behavior: Allows customer measurements that are within range OR smaller than the minimum range.

When It Applies:

  • Accepts measurements at or below the size range
  • Prevents recommending sizes that would be too large
  • Optimizes for snug, fitted, or compression fits

Best For:

  • Athletic and performance wear
  • Compression clothing and undergarments
  • Items where support and stability are important
  • Garments where being too loose compromises function

How Strictness Affects Recommendations

Matching Engine Integration

Flexible Matching Engine Mode

When your quiz uses “Flexible” matching engine mode, strictness settings work as pre-filters:

  1. Strictness Filtering - Eliminates sizes that don’t meet strictness criteria
  2. Algorithm Optimization - Remaining sizes are scored using distance and likelihood algorithms
  3. Best Fit Selection - Recommends the highest-scoring size from eligible options

Exact Matching Engine Mode

With “Exact” matching engine mode:

  • Strictness Irrelevant - All measurements must be exactly within range regardless of strictness settings
  • No Flexibility - Strictness settings are ignored in favor of exact matching
  • Binary Result - Either finds exact match or returns no recommendation

Measurement Interaction

Independent Per-Measurement Control

Each measurement type can have its own strictness level:

  Example Configuration:
Chest: Must Be Inside Range (precise fit for appearance)
Waist: Flexible (comfort priority)
Hip: In Range or Bigger (movement freedom)

Collective Impact

  • Multiple Constraints - Customer must satisfy ALL enabled measurement strictness requirements
  • Filtering Order - Strictness filters are applied before algorithm scoring
  • No Size Found - If no sizes meet all strictness criteria, no recommendation is provided

Practical Applications

Garment-Specific Strategies

Formal Business Attire

Challenge: Professional appearance requires precise fit Solution:

  Chest: Must Be Inside Range (professional silhouette)
Waist: Must Be Inside Range (tailored appearance)  
Hip: Must Be Inside Range (complete formal fit)

Result: Only recommends sizes with precise fit across all measurements

Winter Outerwear

Challenge: Must accommodate layering while maintaining fit Solution:

  Chest: In Range or Bigger (layering space)
Waist: Flexible (comfort with layers)
Hip: In Range or Bigger (outer layer accommodation)

Result: Prevents too-tight recommendations while allowing flexible sizing

Athletic Compression Wear

Challenge: Support and performance require snug fit Solution:

  Chest: Must Be Inside Range (compression effectiveness)
Waist: In Range or Smaller (core support)
Hip: Must Be Inside Range (compression coverage)

Result: Ensures properly supportive fit without loose areas

Casual Comfort Wear

Challenge: Customer comfort and satisfaction priority Solution:

  Chest: Flexible (comfort-optimized recommendations)
Waist: Flexible (variety of fit preferences)
Hip: Flexible (movement and comfort)

Result: Maximum recommendation coverage with algorithm optimization

Advanced Mixed Strategies

Comfort-Performance Hybrid

Use Case: Athletic wear that prioritizes both performance and comfort

  Chest: Must Be Inside Range (performance requirements)
Waist: Flexible (comfort accommodation)
Hip: In Range or Bigger (movement freedom)

Precision-Comfort Balance

Use Case: Semi-formal clothing with comfort considerations

  Chest: Must Be Inside Range (appearance standards)
Waist: Flexible (comfort priority)
Hip: Flexible (natural movement)

Size-Up Prevention

Use Case: Items where oversizing is problematic

  Chest: In Range or Smaller (prevents oversizing)
Waist: Must Be Inside Range (proper fit)
Hip: In Range or Smaller (maintains silhouette)

Implementation Guidelines

Setting Up Strictness Controls

Accessing Strictness Settings

  1. Select Custom Category - Strictness settings only available with Custom garment category
  2. Enable Target Measurements - Configure which measurements to use
  3. Set Individual Strictness - Choose strictness level for each enabled measurement
  4. Test Configuration - Validate with known customer data

Planning Your Strategy

Analyze Product Characteristics:

  • How should the garment fit on the customer?
  • Which measurements are most critical for proper fit?
  • What happens if the fit is slightly off in each dimension?
  • Do customers prefer looser or tighter fits for this item type?

Consider Customer Expectations:

  • What fit feedback do you typically receive?
  • Are returns often due to specific fit issues?
  • Do customers have strong preferences for this product type?
  • How does seasonal variation affect fit preferences?

Testing and Optimization

Gradual Implementation Approach

  1. Start with Draft Status - Test configurations before going live
  2. Use Conservative Settings - Begin with Flexible and tighten as needed
  3. Monitor Customer Response - Track satisfaction and return patterns
  4. Iterate Based on Data - Refine settings based on real-world performance

Performance Monitoring

Key Metrics to Track:

  • Recommendation Rate - Percentage of customers receiving recommendations
  • Customer Satisfaction - Fit feedback and review scores
  • Return Rates - Impact of strictness on product returns
  • Size Distribution - Ensure recommendations cover your size range appropriately

A/B Testing Strategies

  • Split Traffic - Test different strictness configurations
  • Seasonal Testing - Adjust settings for seasonal preferences
  • Product Line Comparison - Compare strictness effectiveness across different products
  • Customer Segment Analysis - Evaluate how different customers respond to strictness levels

Troubleshooting Strictness Issues

Common Problems and Solutions

Too Few Recommendations

Problem: High percentage of “no size found” results Symptoms:

  • Customers frequently don’t receive recommendations
  • Limited size range coverage
  • Customer frustration with sizing process

Solutions:

  • Relax Strictness - Change some measurements to Flexible
  • Review Size Table - Ensure size ranges adequately cover customer base
  • Enable Additional Measurements - Use more measurements for better matching options
  • Validate Customer Data - Ensure measurement input accuracy

Inconsistent Fit Feedback

Problem: Customers report inconsistent fit despite following recommendations Symptoms:

  • Mixed reviews about fit accuracy
  • Some customers satisfied, others disappointed
  • Unclear patterns in fit feedback

Solutions:

  • Align Strictness with Product - Ensure settings match actual garment characteristics
  • Review Size Table Accuracy - Validate that your size ranges reflect actual garment measurements
  • Consider Fabric and Style - Adjust for stretch, drape, and design factors
  • Segment by Customer Type - Consider different settings for different customer groups

Overly Restrictive Results

Problem: Algorithm becomes too conservative in recommendations Symptoms:

  • Only recommends middle sizes
  • Extreme sizes rarely recommended
  • Limited size diversity in recommendations

Solutions:

  • Mixed Strictness Strategy - Use different strictness levels for different measurements
  • Selective Relaxation - Make less critical measurements more flexible
  • Size Table Review - Ensure proper size range coverage and overlap
  • Algorithm Balance - Allow flexibility in at least one measurement dimension

Best Practices Summary

Strategic Planning

  1. Start Simple - Begin with basic configurations and add complexity gradually
  2. Focus on Critical Measurements - Prioritize measurements that most impact customer satisfaction
  3. Document Decisions - Record rationale for strictness choices for future reference
  4. Plan for Iteration - Expect to refine settings based on customer feedback

Ongoing Management

  1. Regular Review - Periodically assess strictness setting effectiveness
  2. Seasonal Adjustments - Modify settings for seasonal fit preferences
  3. Customer Communication - Help customers understand how strictness affects their recommendations
  4. Data-Driven Decisions - Use customer feedback and return data to guide strictness modifications

Measurement strictness settings provide powerful control over SmartSize AI Fit Recommender’s recommendation algorithm, allowing you to balance fit accuracy, customer satisfaction, and recommendation coverage for optimal sizing performance.