Communications on Applied Nonlinear Analysis ISSN: 1074-133X Vol 32 No. 10s (2025) 2757 https://internationalpubls.com A Hybrid Framework for Personalized Digital Marketing: Merging Machine Learning with HCI Principles Anant Manish Singh anantsingh1302@gmail.com Department of Computer Engineering Thakur College of Engineering and Technology (TCET), Mumbai, Maharashtra, India Devesh Amlesh Rai deveshrai162@gmail.com Department of Computer Engineering Thakur College of Engineering and Technology (TCET), Mumbai, Maharashtra, India Shifa Siraj Khan shifakhan.work@gmail.com Department of Information Technology Thakur College of Engineering and Technology (TCET), Mumbai, Maharashtra, India Sanika Satish Lad ladsanika01@gmail.com Department of Computer Engineering Thakur College of Engineering and Technology (TCET), Mumbai, Maharashtra, India Sanika Rajan Shete sanika.shetee@gmail.com Department of Computer Engineering Thakur College of Engineering and Technology (TCET), Mumbai, Maharashtra, India Disha Satyan Dahanukar dishadahanukar@gmail.com Department of Computer Engineering Thakur College of Engineering and Technology (TCET), Mumbai, Maharashtra, India Darshit Sandeep Raut darshitraut28@gmail.com Department of Electronics and Telecommunication Engineering (EXTC) Thakur College of Engineering and Technology (TCET), Mumbai, Maharashtra, India Kaif Qureshi kaif0829@gmail.com Department of Computer Engineering Thakur College of Engineering and Technology (TCET), Mumbai, Maharashtra, India mailto:anantsingh1302@gmail.com mailto:deveshrai162@gmail.com mailto:shifakhan.work@gmail.com mailto:ladsanika01@gmail.com mailto:sanika.shetee@gmail.com mailto:dishadahanukar@gmail.com mailto:darshitraut28@gmail.com mailto:kaif0829@gmail.com Communications on Applied Nonlinear Analysis ISSN: 1074-133X Vol 32 No. 10s (2025) 2758 https://internationalpubls.com Article History: Received: 12-01-2025 Revised: 15-02-2025 Accepted: 01-03-2025 Abstract: Digital marketing increasingly relies on data science for audience targeting and performance analytics. However, these efforts often overlook the role of human- computer interaction (HCI) in shaping user experiences, leading to suboptimal engagement despite algorithmic personalization. Existing models emphasize prediction and targeting but rarely integrate HCI principles into the design and deployment of digital campaigns. This disconnect results in high bounce rates, low interaction quality and poor user retention. This paper bridges the gap by proposing an integrated framework that combines data-driven decision-making with user-centred design. The framework applies machine learning to behavioural data while embedding HCI heuristics to personalize and enhance digital interfaces. Experimental deployment on an e-commerce platform showed a 20.4% increase in user engagement and a 14.7% boost in conversion rates, validated through A/B testing over a four-week period with 10,000 users. These improvements were statistically significant (p < 0.05). The proposed framework can be adopted by digital marketers and UX teams to co-design campaigns that are both analytically optimized and experientially intuitive. The current study is limited to short-term interactions on a single platform. Future work will generalize the model across industries and explore long-term behavioural adaptation and brand loyalty impact. Keywords: data-driven marketing, human-computer interaction, user engagement, machine learning, conversion optimization, user-centric design, digital advertising 1. Introduction 1.1 Background Digital marketing has evolved significantly with the advent of data science and HCI. Marketers now have access to vast amounts of user data, enabling personalized and targeted campaigns. However, the challenge lies in effectively integrating this data with user-friendly interfaces to enhance user experience and engagement. 1.2 Problem Statement Despite the availability of advanced analytics tools, many digital marketing campaigns fail to achieve optimal user engagement due to a lack of consideration for HCI principles in the design of marketing interfaces. 1.3 Objectives β€’ To develop a framework that integrates data science techniques with HCI principles for digital marketing. β€’ To evaluate the effectiveness of this integrated approach in enhancing user engagement and conversion rates. β€’ To provide actionable insights for marketers on optimizing digital campaigns through user-centric design Communications on Applied Nonlinear Analysis ISSN: 1074-133X Vol 32 No. 10s (2025) 2759 https://internationalpubls.com 1.4 Scope This study focuses on online advertising platforms, analysing user interactions with digital ads and landing pages. The proposed framework is applicable to various industries including e- commerce, education and entertainment. 1.5 Structure The paper is organized as follows: Section 2 reviews related literature; Section 3 presents the methodology; Section 4 discusses the results and findings; Section 5 provides a discussion; and Section 6 concludes the paper with limitations and future research directions. 2. Literature Survey Paper Title Methodology Key Findings Gaps Identified Zhabiz Gharibshah and Xingquan Zhu. 2021. User Response Prediction in Online Advertising. ACM Comput. Surv. 54, 3, Article 64 (April 2022), 43 pages. https://doi.org/10.1145/3 446662 Machine Learning Developed models for user response prediction in online advertising. Lack of integration with HCI principles. Li, N., Arava, S. K., Dong, C., Yan, Z., & Pani, A. (2018). Deep neural net with attention for multi-channel multi- touch attribution (arXiv:1809.02230v1). arXiv. https://doi.org/10.48550/ arXiv.1809.02230 Deep Learning Proposed a multi- touch attribution model using deep neural networks. Limited focus on user experience factors. Cui, Y., Tobossi, R., & Vigouroux, O. (2018). Modelling customer online behaviours with neural networks: Applications to conversion prediction and advertising retargeting (arXiv:1804.07669). arXiv. https://doi.org/10.48550/ arXiv.1804.07669 Neural Networks Modelled customer online behaviours for conversion prediction. Absence of user interface considerations. https://doi.org/10.1145/3446662 https://doi.org/10.1145/3446662 https://doi.org/10.48550/arXiv.1809.02230 https://doi.org/10.48550/arXiv.1809.02230 https://doi.org/10.48550/arXiv.1804.07669 https://doi.org/10.48550/arXiv.1804.07669 Communications on Applied Nonlinear Analysis ISSN: 1074-133X Vol 32 No. 10s (2025) 2760 https://internationalpubls.com France, S. L., & Ghose, S. (2019). Marketing analytics: Methods, practice, implementation, and links to other fields. Expert Systems with Applications, 117, 272– 289. https://doi.org/10.1016/j. eswa.2018.11.002 Literature Review Explored marketing analytics methods and practices. Insufficient emphasis on HCI integration. Existing studies predominantly focus on algorithmic approaches to digital marketing often neglecting the importance of user experience design. This research aims to fill this gap by incorporating HCI principles into data-driven marketing strategies. 3. Methodology 3.1 Data Collection User interaction data was collected from an e-commerce platform including click-through rates, time spent on pages and conversion rates. Additionally, user feedback was gathered through surveys assessing the usability of the platform. 3.2 Data Analysis Machine learning algorithms such as decision trees and neural networks were employed to analyse user behaviour and predict conversion likelihood. User interface elements were evaluated based on HCI principles, focusing on usability and user satisfaction. 3.3 Framework Development An integrated framework was developed that combines predictive analytics with user-centric design guidelines. This framework aims to personalize marketing strategies by aligning them with user preferences and behaviours. Figure 1: Framework Development https://doi.org/10.1016/j.eswa.2018.11.002 https://doi.org/10.1016/j.eswa.2018.11.002 Communications on Applied Nonlinear Analysis ISSN: 1074-133X Vol 32 No. 10s (2025) 2761 https://internationalpubls.com 3.4 Evaluation The effectiveness of the proposed framework was evaluated through A/B testing, comparing user engagement and conversion rates before and after implementing the personalized strategies. Let 𝑓(π‘₯) be the neural net output for user features π‘₯, then: πΆπ‘œπ‘›π‘£π‘’π‘Ÿπ‘ π‘–π‘œπ‘› π‘ƒπ‘Ÿπ‘œπ‘π‘Žπ‘π‘–π‘™π‘–π‘‘π‘¦ = 𝜎(π‘Š β‹… 𝑓(π‘₯) + 𝑏) Where 𝜎 is the sigmoid activation, W is the learned weight vector and b is the bias term. 4. Results and Findings 4.1 Data Analysis The machine learning models identified key factors influencing user engagement including personalized content and intuitive navigation. The HCI evaluation highlighted areas for improvement in user interface design such as simplifying navigation and enhancing visual appeal. Figure 2: Relative Importance of Engagement Drivers Identified by Machine Learning Models 4.2 Framework Implementation Implementing the integrated framework led to a 20% increase in user engagement and a 15% improvement in conversion rates. These results were statistically significant with a p-value of less than 0.05. Communications on Applied Nonlinear Analysis ISSN: 1074-133X Vol 32 No. 10s (2025) 2762 https://internationalpubls.com Figure 3: Comparative Analysis of User Engagement and Conversion Rates Before and After Framework Implementation 4.3 Validation Real-time validation was conducted by deploying the personalized marketing strategies on the platform and monitoring user interactions. The observed outcomes corroborated the findings from the A/B testing, confirming the effectiveness of the integrated approach. Figure 4: Validation of Framework Effectiveness through A/B Testing and Real-Time Monitoring 5. Discussion 5.1 Interpretation of Results The integration of data science techniques with HCI principles resulted in more personalized and user-friendly marketing strategies, leading to enhanced user engagement and conversion rates. Communications on Applied Nonlinear Analysis ISSN: 1074-133X Vol 32 No. 10s (2025) 2763 https://internationalpubls.com 5.2 Implications Marketers should consider incorporating user experience design into their data-driven strategies to optimize campaign performance. 5.3 Limitations The study was limited to a single e-commerce platform and the findings may not be generalizable to other industries or platforms. 5.4 Future Research Future studies could explore the application of the proposed framework across different industries and platforms as well as investigate the long-term effects of personalized marketing strategies on user behaviour. 6. Conclusion This research demonstrates the value of integrating data science and HCI in digital marketing. By aligning marketing strategies with user preferences and behaviors, marketers can enhance user engagement and conversion rates. The proposed framework offers a novel approach to optimizing digital marketing campaigns providing a foundation for future research in this area. References [1]. Kaponis, A., Maragoudakis, M., & Sofianos, K. C. (2024). Enhancing User Experiences in Digital Marketing through Machine Learning: Cases, Trends, and Challenges. [2]. Gupta, G., Chintale, P., Korada, L., Mahida, A. H., Pamulaparthyvenkata, S., & Avacharmal, R. (2024). The Future of HCI Machine Learning, Personalization, and Beyond. In Driving Transformative Technology Trends With Cloud Computing (pp. 309-327). IGI Global. [3]. Wang, X., & Hu, B. (2024). Machine Learning Algorithms for Improved Product Design User Experience. IEEE Access. [4]. Wu, Y. (2025). Analysis of Cross-Border E-Commerce HCI Network Marketing Strategies Based on Social Media and AI-Powered CAD. Computer-Aided Design and Applications, 22(S6), 147-59. [5]. Rathi, S. R., Jadhav, N., Raut, A., Navhal, A., & Patil, M. (2025). Predictive Analytics Using Machine Learning for Enhanced Online Advertising. In Bridging Academia and Industry Through Cloud Integration in Education (pp. 281-306). IGI Global Scientific Publishing. [6]. Liang, Y., Deng, R., Lin, W., Deng, R., Zhu, X., & Yu, L. (2025). Modeling and Reinforcement Learning Assessment System for Quality Improvement of Advertising Design. Computer-Aided Design & Applications, 21, 188-200. [7]. Abdullah, C. M., & Zeebaree, S. (2025). The Role of Machine Learning in Enhancing Marketing Strategies within Cloud-based Enterprise Systems. Asian Journal of Research in Computer Science, 18(5), 32-54. Communications on Applied Nonlinear Analysis ISSN: 1074-133X Vol 32 No. 10s (2025) 2764 https://internationalpubls.com [8]. Halkiopoulos, C., Gkintoni, E., Aroutzidis, A., & Antonopoulou, H. (2025). Advances in Neuroimaging and Deep Learning for Emotion Detection: A Systematic Review of Cognitive Neuroscience and Algorithmic Innovations. Diagnostics, 15(4), 456. [9]. Razzaq, K., & Shah, M. (2025). Machine learning and deep learning paradigms: From techniques to practical applications and research frontiers. Computers, 14(3), 93. [10]. Ibrahim, N. M., Abiduzzaman, S. M., Raziff, A. R. A., & Shah, A. (2025). A Collaborative Filtering Approach Using Machine Learning and Business Intelligence: A Critical Review. International Journal on Perceptive and Cognitive Computing, 11(1), 41-49. [11]. Chen, Y., & Meng, D. (2025). Optimization of Visual Communication Design Scheme by Combining Computer-Aided Design and Deep Learning. Computer-Aided Design & Applications, 22, 253-267. [12]. SBIAI, F. (2025). AI-Powered Recommendation Systems: Exploring their Impact on Customer-Business Interaction. International Journal of Innovative Science and Research Technology, 10(4), 1332-1339. [13]. Pasch, S., & Ha, S. Y. (2025). Human-AI Interaction and User Satisfaction: Empirical Evidence from Online Reviews of AI Products. arXiv preprint arXiv:2503.17955.