Abstract

Determinants of online consumer’s purchase decisions are of long-term interest to researchers and practitioners. Since product photos directly aid consumers’ understanding of products, retailers often put a lot of effort into polishing them. However, there is limited research on the impact of product photos on purchase decisions. Most previous studies took an experiment-based approach, which delivered strict theories on some aspects of product photos. This research takes advantage of image-processing techniques to study product photos’ impact. These techniques allow us to investigate a large set of photo characteristics simultaneously in an empirical study. To rule out possible confounding factors, we collect a dataset from a social shopping Website, which has a simple interface allowing users to judge products mainly based on their photos. We examine product photo characteristics from the aspects of information, emotion, aesthetics, and social presence. We found that consumers prefer product photos with a larger key object, lower entropy on key objects, a warmer color, a higher contrast, a higher depth-of-field, and more social presences. This research introduces a Big Data-based approach to study the impact of e-commerce systems’ visual features on consumers.

Share

COinS