Uncovering Latent Shoppers - Bridging the Gap Between Stated Preferences and Actual Shopper Behavior
Understanding consumer behavior in the retail industry goes far beyond traditional market research and shared panel data. It involves delving deep into the dichotomy between what consumers say and what they do. By leveraging store-level data and advanced AI models, we can inform portfolio and price pack decisions with the only insights that matter - what will happen at the shelf?
Dichotomy: Stated Preferences Versus Real Behavior
Take toothpaste as an example. Primary market research indicates consumers desire toothpaste that freshens breath, whitens teeth, fights cavities, and tastes good. These stated preferences, however, don't always translate into the consumer's in-store decisions.
The buying decision often takes a different course in the actual shopping scenario. For instance, a budget-conscious shopper in a dollar store might opt for a less expensive product even though it lacks some of the features they initially wanted. This disparity underscores the necessity of studying shopper opinions and real-world shopper purchase data. This is what we have found working with our CPG customers in over 100 different category/retail combinations.
The Chameleon Effect: Shifting Shopper Behavior Across Stores
Shopper behavior also fluctuates across different channels and chains. For example, the shopping patterns at Walmart, Target, Kroger, and Dollar General can vary for the same shopper, influenced by unique store missions and budgetary constraints.
Insights gleaned from store-level data paint a vivid picture of these variations. Our analysis reveals that premium items were still relevant at Target, while shoppers prefer mid-tier and value brands at Dollar General. On the other hand, Walmart sees dominance in a specific pack size that resonates most with its customers.
Gone are the days when brands can apply a uniform strategy across all retailers. Today's market requires a retailer-specific approach. It's not merely about whether changes are necessary, but rather about determining the optimal brand and pack size strategy for each retail outlet.
The Intersection of Store-Level Data and Machine Learning
Store level-sales data, decoded by machine learning algorithms, allows for insights about the nuance of shopper behavior by store chain. By analyzing every single transaction across a chain, we can capture the unfiltered, real-world decisions of shoppers.
Harnessing the power of store-level data and machine learning together allows brands to drive the most appropriate overall strategy while considering the nuances across their retail customers.
I would love to hear your thoughts on whether there is a difference between what consumers say they prefer versus what shoppers actually buy.