Article published on Daniels Insights, thought leadership from Purdue’s Business School. https://business.purdue.edu/daniels-insights/posts/2026/turning-customer-behavior-into-strategy-smarter-segmentation.php

Understanding why customers choose, stay or switch has always been the challenge and the foundation of effective retail strategy. New research from the Daniels School’s Qiang Liu on benefit segmentation demonstrates that analyzing behavior alone is not enough. Business analysts need to connect consumer action with their underlying motivations to unlock competitive advantage.

The findings from the research, “Incorporating switching reasons into a factor-analytic choice model: A study on benefit segmentation of physicians,” recently published in Quantitative Marketing and Economics, extend beyond healthcare. Associate Professor of Marketing Liu and his coauthors provide insights for any organization managing customer choice, churn or brand competition.

The limits of traditional data

Many organizations rely heavily on behavioral data — purchase histories, switching patterns or usage trends — to guide segmentation and targeting. While the data reveals patterns, it doesn’t guarantee analysts discover the real unicorn: consumer motivation.

The research shows that traditional factor-analytic choice models can map relationships, identifying which customers behave similarly or which products compete closely, but they fall short in explaining the underlying drivers of those choices.

This means a company might know that two customer segments behave differently, but not whether those differences are driven by price sensitivity, quality expectations, convenience or other factors. Without that insight, targeting and positioning strategies remain incomplete.

Combining behavior with “why”

Liu’s research shows that combining observed behavior with self-reported explanations for why customers switch products or services “anchors” behavior to motivation.

By incorporating short explanations for customer churn, researchers were able to identify distinct benefit drivers such as efficacy, side effects and cost savings, turning an anonymous behavioral map into a clearly labeled decision framework.

The findings indicate that businesses should gather customer behavior data and create a means for systematically capturing why customers change.

Start with real-world behavior — but don’t stop there

The research emphasizes the importance of using actual choice data (not just surveys) because it reflects real decisions in real contexts. This improves accuracy and relevance.

Behavior alone is incomplete. As the study highlights, “observed choices alone still do not reveal the benefit labels behind behavior.” Instead, use transactional and behavioral data as your foundation, and pair it with qualitative inputs that explain decision-making.

Don’t confuse patterns with strategy

Advanced analytics can generate sophisticated “maps” of customer behavior. But without clear interpretation, these maps remain abstract.

The study shows that traditional models produce unnamed, flexible dimensions that are difficult to translate into business action. Analytics must lead to interpretable outputs. If your models cannot clearly answer “what customers value most,” they are unlikely to drive effective targeting or positioning.

Capture switching and churn reasons systematically

The most actionable recommendation from the research is also the most practical: collect structured “why” data at key decision points.

In the study, approximately 85% of switching reasons could be categorized into a small set of meaningful benefit drivers. This demonstrates that even simple inputs — short text responses or categorized reasons — can dramatically improve insight quality and unlock significant strategic value.

A practical mindset shift

The broader implication of this research is a shift in how organizations approach segmentation and targeting.

Instead of relying solely on who customers are (demographics) or what they do (behavior), organizations should focus on why they choose. Importantly, such insights scale across industries, from financial services to consumer goods to technology — anywhere customers make repeated choices and occasionally switch.

For many organizations, the barrier is not technology but mindset. Behavioral data is abundant and easy to analyze, while “why” data requires intentional design and integration. Combining the two creates a far more complete and actionable view of the customer, one that allows businesses to create products and services that customers value more.