Which Photographic Features of Product Images Impact Consumer Attractiveness?
Bibliographic record
Abstract
The determinants influencing online shopping decisions have long been a focal point of interest for both business practitioners and academic researchers. Among these factors, product imagery stands out as a critical element. However, there remains a notable research gap in understanding the specific features of product images that significantly impact consumers' purchasing decisions in the online context. While the role of product imagery is acknowledged, further investigation is needed to identify which particular aspects of these images are most influential in shaping consumer decision-making processes. The majority of previous research about product images used survey-based methods to measure image quality based on interviewee’s satisfaction and rating instead of data-based analysis. Hence, this research paper aims to investigate the relationship between product photography and customer attractiveness on e-commerce platforms by exploring what photographic characteristics could contribute to better designing product images that captivate consumers and ultimately enhance sales. Additionally, this study aims to explore potential differences in purchasing behavior between male and female consumers, providing a complementary dimension to the research findings. The analysis is conducted using data-driven methodologies, with a specific focus on key features of product images. These include aesthetic appeal, embedded messaging, and social presence, all of which are central to the investigation's scope. The author collects data through a crawler tool and organizes it into a raw dataset (both for males and females). Next, image-processing techniques and feature engineering are applied to conduct the final dataset used for linear regression. Then, backward elimination contributes to determining the best-performed linear regression model, which illustrates the photographic features which are significant to the impingement of sales numbers. As a result, it is confirmed that male clients are more affected by the amount of information contained and the proportion of the products in the product image. In contrast, female clients take notice of the appearance of human models.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.008 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.006 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".