Predictive Modeling of Customer Purchase Behavior in Social Media Advertising: A Logistic Regression Approach
Abstract
This study investigates the impact of demographic factors on purchase behavior in social media advertising, addressing a key issue for marketers: identifying which characteristics can enhance targeted ad strategies. Using logistic regression, the research examines how age and estimated salary influence the probability of making a purchase, offering insights into consumer decision-making in digital environments. The analysis draws on a dataset of 400 observations from a survey of active social media users across platforms like Instagram, Facebook, and Twitter. A logistic regression model was trained to assess the relationship between demographic predictors and purchase outcomes, with subsequent testing for predictive accuracy. Both age and estimated salary emerged as significant predictors, with each showing a positive association with purchase probability. Marginal effects analysis highlighted the stronger influence of age on purchase likelihood, while estimated salary, though statistically significant, showed a subtler effect. Additionally, odds ratios confirmed the predictive strength of these factors. Model performance was evaluated using accuracy, precision, and recall metrics derived from a confusion matrix, demonstrating high reliability in predicting purchasers and non-purchasers, albeit with a conservative tendency. The distribution of predicted probabilities indicated strong confidence in classifying non- purchasers, supporting the model’s cautious approach to positive predictions. These findings provide practical insights for marketers seeking to optimize ad targeting by leveraging demographic data. By understanding the demographic drivers of purchase decisions in social media contexts, this study contributes to the development of more efficient and effective advertising strategies, ultimately enhancing customer engagement. Future research could expand this model by incorporating additional demographic or psychographic variables, facilitating a more nuanced approach to predicting purchase behavior in digital advertising.Keywords:
Customer , Social Media , Logistic Regression ApproachReferences
Akar, E., & Topçu, B. (2011). An Examination of the Factors Influencing Consumers’ Attitudes Toward Social Media Marketing. Journal Of Internet Commerce, 10(1), 35-67. https://doi.org/10.1080/15332861.2011.558456
Chaffey, D., & Ellis-Chadwick, F. (2019). Digital Marketing: Strategy and Implementation. Pearson Education.
Hosmer, D. W., Lemeshow, S., & Sturdivant, R. X. (2013). Applied Logistic Regression (3rd ed.). John Wiley & Sons.
Kaplan, A. M., & Haenlein, M. (2009). Users of the world, unite! The challenges and opportunities of social media. Business Horizons, 53(1), 59-68. https://doi.org/10.1016/j.bushor.2009.09.003
Kotler, P., & Keller, K. L. (2016). Marketing Management (15th ed.). Pearson.
Menard, S. (2010). Logistic Regression: From Introductory to Advanced Concepts and Applications. https://doi.org/10.4135/9781483348964
Naem, M., & Okafor, S. (2019). User-Generated Content and Consumer Brand Engagement. En Advances in marketing, customer relationship management, and e-services book series (pp. 193-220). https://doi.org/10.4018/978-1-5225-7344-9.ch009
Peng, C. J., Lee, K. L., & Ingersoll, G. M. (2002). An Introduction to Logistic Regression Analysis and Reporting. The Journal Of Educational Research, 96(1), 3-14. https://doi.org/10.1080/00220670209598786
Stieglitz, S., Mirbabaie, M., Ross, B., & Neuberger, C. (2017). Social media analytics – Challenges in topic discovery, data collection, and data preparation. International Journal Of Information Management, 39, 156-168. https://doi.org/10.1016/j.ijinfomgt.2017.12.002
