Evaluating the Role of Social Media Advertisements on Consumer Engagement Using Machine Learning

Social media advertisements are yielding growing influence on the behavior of consumers, and indeed become a key part of digital marketing strategies. The purpose of this paper is to assess the effect of social media advertisements in generating customer engagement using machine learning methods. The study utilizes the "Online Shoppers Purchasing Intention" dataset, which contains data on user interactions with online advertisements and shopping behavior. Data pre processing is done to fill in missing values and handle categorical variables, feature engineering is done to create new variables like advertisement click rate and time spent on page. In order to build and assess machine learning models like Logistic Regression and Random Forest, the dataset is split into training, validation and test sets. The results are evaluated using accuracy, precision, recall, F1-score, and ROC-AUC as the hyperparameters are tuned to optimize model performance. Results show that certain advertisement attributes as well as user demographics have a significant effect on the level of engagement and Random Forest is the best performing model. Findings from this research will help digital marketers know that it is possible to engage with consumers by using their behavior and demographics to target advertisements, hence improving the prospects of the marketing outcomes.