Measuring Information Richness in Product Images: Implications for Online Sales

TL;DR

This paper introduces a new metric called k-value to measure the information richness of product images, validating its alignment with human perception and exploring its complex impact on consumer purchase behavior in online shopping.

Contribution

It proposes and validates a novel metric for image information richness using Vision Transformers and clustering, revealing its effects on decision time and purchase likelihood.

Findings

Higher k-value shortens decision time

Richer images paradoxically reduce purchase propensity

k-value correlates with human perception of information richness

Abstract

A common challenge for e-commerce sellers is to decide what product images to display on online shopping sites. In this paper, we propose and validate a novel metric, k-value, to quantify the information richness of an image set, and we further investigate its effect on consumers' purchase decisions. We leverage patch-level embeddings from Vision Transformers (ViT) and apply k-means clustering to identify distinct visual features, defining k-value as the number of clusters. An online experiment demonstrates that k-value aligns with human-perceived information richness, validating the metric. A simulated online shopping experiment further reveals a significant yet counterintuitive result: while an image set with a higher k-value (richer information) shortens decision time, it paradoxically reduces purchase propensity. Our findings illuminate the complex relationship between visual information richness and consumer behavior, providing sellers a quantifiable tool for image selection.