Application of numerical methods for optimizing visual elements in e-commerce

Cover Page

Cite item

Full Text

Open Access Open Access
Restricted Access Access granted
Restricted Access Subscription or Fee Access

Abstract

The article discusses the use of numerical methods to optimize the design elements of product cards. The discount block, one of the key elements significantly influencing sales, is selected as the object of study. The aim of the research is to improve the click-through rate (CTR) of product cards by analyzing and optimizing visual parameters such as color, font size, block placement, discount format, and device type. To achieve this goal, a regression model was developed to predict CTR for new parameter combinations without the need for full-cycle testing and to evaluate the significance of the analyzed parameters. The results show that the most impactful factors on CTR are background color, font size, and the placement of the discount block. The proposed approach reduces the number of required tests, accelerates the optimization process, and can be adapted to other design elements, such as call-to-action buttons or stock availability indicators.

Full Text

Restricted Access

About the authors

Andrei A. Chmelev

Wildberries LLC

Author for correspondence.
Email: an.chmelev@gmail.com

senior full stack engineer, technical lead, specialist in applied mathematics and computer science, mathematician, system programmer

Russian Federation, Moscow

Natalia V. Grineva

Financial University under the Government of the Russian Federation

Email: ngrineva@fa.ru
ORCID iD: 0000-0001-7647-5967

Cand. Sci. (Econ.), associate professor, Department of Information Technology

Russian Federation, Moscow

References

  1. Ku E., Lau T. The impact of discounts on consumer behavior: A comprehensive review. Journal of Retailing and Consumer Services. 2015.
  2. Lee J., Chen C. The role of visual parameters in marketing: A regression analysis approach. Journal of Marketing Research. 2020.
  3. Box G.E.P., Hunter W.G., Hunter J.S. Statistics for experimenters: Design, innovation, and discovery. John Wiley & Sons, 1978.
  4. Montgomery D.C. Design and analysis of experiments. 9th ed. Wiley, 2017.
  5. Bishop C.M. Pattern recognition and machine learning. Springer, 2006.
  6. Hastie T., Tibshirani, R., Friedman J. The elements of statistical learning: Data mining, inference, and prediction. Springer, 2009.
  7. Goodfellow I., Bengio Y., Courville A. Deep learning. MIT Press. 2016.
  8. Pedregosa F., Varoquaux G., Gramfort A. et al. Scikit-learn: Machine learning in Python. Journal of Machine Learning Research. 2011. No. 12. Pp. 2825–2830.
  9. Handbook on D-optimal design. National Institute of Standards and Technology (NIST), 2017. URL:
  10. McKinney W. Python for data analysis: Data wrangling with Pandas, NumPy, and IPython. O’Reilly Media, 2017.

Supplementary files

Supplementary Files
Action
1. JATS XML
Download
2. Fig. 1. Dependence of the maximum VIF on the number of experiments in a fractional factorial experiment

Download (95KB)
Indexing metadata
3. Fig. 2. Distribution of CTR values based on the analysis of discount design parameters

Download (54KB)
Indexing metadata
4. Fig. 3. Impact of factors on CTR based on regression analysis results

Download (273KB)
Indexing metadata
5. Fig. 4. Residuals vs Fitted Values Plot

Download (71KB)
Indexing metadata