Kano and factor analysis for a European online fashion

CLIENT CHALLENGES

A Europe-based online fashion retailer engaged us to analyse multi-source survey data to refine its mobile and desktop platforms and prioritise feature improvements
The client had collected over 12,000 survey responses across five European markets (the UK, Germany, France, Spain, Italy), focusing on user satisfaction, buying behaviour and expectations from platform features
They sought clarity on which features truly delighted users versus those that were expected by default and also aimed to reduce redundancy in survey dimensions through data simplification

Step 1: Data integration and standardisation
- Harmonised survey data across markets, mapping different scales (e.g., 1-5 satisfaction vs binary satisfaction) to a uniform Likert scale
- Mapped responses for feature categories such as the following:
  - “One-click checkout”
  - “Real-time inventory updates”
  - “AI-based outfit recommendations”
  - “Mobile-first design”
Step 2: Kano analysis
- Kano model was applied to classify features into the following:
  - Must-haves (basic needs)
  - Performance needs (linear satisfaction)
  - Delighters (unexpected feature satisfaction)
- Respondents evaluated each feature using both functional (like) and dysfunctional (dislike) forms
Step 3: Factor analysis
- Conducted factor analysis (FA) to group 24 survey questions into latent dimensions
- Reduced 24 questions to 4 major factors explaining 76% of variance:
  - Convenience factor (checkout, delivery, navigation)
  - Trust factor (data security, return policy clarity)
  - Personalisation factor (recommendations, tailored content)
  - Engagement factor (mobile app features, loyalty programme)

Prioritise development efforts on high impact such as improved stock alerts, loyalty programs and AR try-on
Roll out segment features based on regional needs, such as enhancing privacy policy transparency in GDPR-sensitive markets
Simplify future survey efforts, reducing respondent fatigue while focusing on four key insight-driving dimensions
Boost user satisfaction scores by 17% quarter-over-quarter after implementation of the top three features

Download as PDF