Leveraging AI to Personalize HR Marketing Campaigns: A Data-Driven Approach

The research proposes an AI-driven personalization framework for enhancing the efficiency and engagement of HR marketing campaigns. The system integrates real-time data processing, collaborative filtering, and feedback loops to dynamically recommend job opportunities tailored to individual candidate preferences. Using an HR-related dataset from Kaggle, the framework preprocesses data by handling missing values, scaling numerical features via Min-Max Scaling, and reducing dimensionality using Principal Component Analysis (PCA). Collaborative Filtering is employed to predict candidate preferences through matrix factorization, dynamically updating recommendations based on real-time user interactions. The experimental evaluation highlights the framework's superior performance compared to traditional methods. Click-Through Rate (CTR) improved significantly, with AI-driven personalization achieving 30% compared to 18% from rule-based methods and 12% from the baseline. Accuracy analysis revealed that Collaborative Filtering outperformed random and content-based methods, achieving the highest precision (85%), recall (88%), and F1-score (86%). These results underscore the effectiveness of AI in aligning candidate preferences with recruitment goals while ensuring dynamic adaptation through feedback. The proposed system also seamlessly integrates personalized insights into HR marketing channels such as job portals, email campaigns, and social media advertisements, optimizing recruitment processes and enhancing user engagement. Future research aims to extend the dataset to include diverse candidate profiles, incorporate multi-modal data sources, and leverage deep learning for improved recommendation accuracy. Additionally, explainability techniques will be explored to ensure transparency and build trust among users. This framework demonstrates the transformative potential of AI-driven personalization in reshaping HR marketing strategies.