Optimizing Logistic Regression for Digital Marketing Campaigns: Insights from Hyperparameter Tuning with Optuna

Budiman Budiman, Nur Alamsyah, Elia Setiana, Fikri Muhamad Fahmi

Abstract


The shift from mass media advertising to digital marketing driven by the internet revolution highlights the need for data-driven strategies and emerging technologies like Artificial Intelligence (AI). This study aims to develop effective strategies for digital marketing campaigns that enhance customer engagement and increase conversion rates. Key factors such as CampaignChannel, CampaignType, AdSpend, and demographic characteristics (Age, Gender, Income) were analyzed about performance metrics like ConversionRate and WebsiteVisits. A dataset with 20 customer demographics and campaign details features was processed and evaluated using machine learning models, including Logistic Regression, Random Forest, and XGBoost. Pre-processing involved handling missing values, feature selection, and splitting data into training and testing sets. Hyperparameter tuning using Optuna optimized the Logistic Regression Model, achieving the best performance with 89% accuracy. The findings reveal significant relationships between campaign factors and customer behaviour, providing actionable insights to enhance ROI (ROI). This study contributes to a machine learning-based framework for effective segmentation, personalized interactions, and efficient marketing budget management. The study advances AI applications in digital marketing by addressing challenges like data dynamics and shifting business conditions, paving the way for adaptive and data-driven strategies.


Keywords


Digital Marketing; Customer Engagement; Machine Learning; Logistic Regression; Campaign Optimization; Hyperparameter; Optuna

Full Text:

PDF

References


B. Peyravi, J. Nekrošienė, and L. Lobanova, ‘Revolutionised Technologies for Marketing: Theoretical Review With Focus On Artificial Intelligence’, Verslas: teorija ir praktika, vol. 21, no. 2, pp. 827–834, 2020.

Q. Yang, P. Li, X. Xu, Z. Ding, W. Zhou, and Y. Nian, ‘A Comparative Study on Enhancing Prediction in Social Network Advertisement Through Data Augmentation’, in 2024 4t,’International Conference on Machine Learning and Intelligent Systems Engineering (MLISE), Jun. 2024, pp. 214–218. doi: 10.1109/MLISE62164.2024.10674203.

K. Jin, Z. Z. Zhong, and E. Y. Zhao, ‘Sustainable Digital Marketing Under Big Data: An AI Random Forest Model Approach,’ IEEE Transactions on Engineering Management, vol. 71, pp. 3566–3579, 2024, doi: 10.1109/TEM.2023.3348991.

B. S. Arasu, B. J. B. Seelan, and N. Thamaraiselvan, ‘A Machine Learning-Based Approach To Enhancing Social Media Marketing,’ Computers & Electrical Engineering, vol. 86, p. 106723, Sep. 2020, doi: 10.1016/j.compeleceng.2020.106723.

M. Boujrad and Y. el M. N. lamlili, ‘A New Artificial Intelligence-Based Strategy for Digital Marketing Reinforcement’, in Innovations in Smart Cities Applications Volume 4, M. Ben Ahmed, İ. Rakıp Karaș, D. Santos, O. Sergeyeva, and A. A. Boudhir, Eds., Cham: Springer International Publishing, 2021, pp. 689–699. doi: 10.1007/978-3-030-66840-2_52.

R. Sarath Kumar Boddu, A. A. Santoki, S. Khurana, P. Vitthal Koli, R. Rai, and A. Agrawal, ‘An Analysis To Understand The Role Of Machine Learning, Robotics And Artificial Intelligence In Digital Marketing’, Materials Today: Proceedings, vol. 56, pp. 2288–2292, Jan. 2022, doi: 10.1016/j.matpr.2021.11.637.

M. Marić, O. Grljević, and L. Gluščević, ‘Application Of Artificial Intelligence In Digital Marketing’, Anali Ekon fak Subotica, no. 52, pp. 21–37, 2024, doi: 10.5937/AnEkSub2300033M.

P. van Esch and J. Stewart Black, ‘Artificial Intelligence (AI): Revolutionizing Digital Marketing’, Australasian Marketing Journal, vol. 29, no. 3, pp. 199–203, Aug. 2021, doi: 10.1177/18393349211037684.

D. Dumitriu and M. A.-M. Popescu, ‘Artificial Intelligence Solutions for Digital Marketing’, Procedia Manufacturing, vol. 46, pp. 630–636, Jan. 2020, doi: 10.1016/j.promfg.2020.03.090.

N. Saud Abd, O. Salim Atiyah, M. Taher Ahmed, and A. Bakhit, ‘Digital Marketing Data Classification by Using Machine Learning Algorithms’, IJEEE, vol. 20, no. 1, pp. 245–256, Jun. 2024, doi: 10.37917/ijeee.20.1.23.

K. Singhal, J. N. Singh, and V. Sharma, ‘Enabling Autonomous Digital Marketing: A Machine Learning Approach for Consumer Demand Forecasting’, in 2024 IEEE International Conference on Computing, Power and Communication Technologies (IC2PCT), Feb. 2024, pp. 1903–1908. doi: 10.1109/IC2PCT60090.2024.10486327.

C. Wang, ‘Efficient Customer Segmentation In Digital Marketing Using Deep Learning With Swarm Intelligence Approach’, Information Processing & Management, vol. 59, no. 6, p. 103085, Nov. 2022, doi: 10.1016/j.ipm.2022.103085.

V. Singh, B. Nanavati, A. K. Kar, and A. Gupta, ‘How to Maximize Clicks for Display Advertisement in Digital Marketing? A Reinforcement Learning Approach’, Inf Syst Front, vol. 25, no. 4, pp. 1621–1638, Aug. 2023, doi: 10.1007/s10796-022-10314-0.

M. Zeeshan and K. Saxena, ‘Explorative Study of Artificial Intelligence in Digital Marketing’, in Proceeding of the International Conference on Computer Networks, Big Data and IoT (ICCBI - 2019), A. P. Pandian, R. Palanisamy, and K. Ntalianis, Eds., Cham: Springer International Publishing, 2020, pp. 968–978. doi: 10.1007/978-3-030-43192-1_107.

Q. Han, C. Lucas, E. Aguiar, P. Macedo, and Z. Wu, ‘Towards Privacy-Preserving Digital Marketing: An Integrated Framework For User Modeling Using Deep Learning On A Data Monetization Platform’, Electron Commer Res, vol. 23, no. 3, pp. 1701–1730, Sep. 2023, doi: 10.1007/s10660-023-09713-5.

Y. Lahbabi, S. Raki, H. C. Lamrani, and S. Dehbi, ‘Machine Learning In Digital Marketing.’, MENACIS2021, Nov. 2021, [Online]. Available: https://aisel.aisnet.org/menacis2021/28

M. S. Ullal, I. T. Hawaldar, R. Soni, and M. Nadeem, ‘The Role of Machine Learning in Digital Marketing’, Sage Open, vol. 11, no. 4, p. 21582440211050394, Oct. 2021, doi: 10.1177/21582440211050394.

G. Gürsoy, A. Varol, and S. Varol, ‘Impact of Machine Learning in Digital Marketing Applications’, in 2022 3rd International Informatics and Software Engineering Conference (IISEC), Dec. 2022, pp. 1–6. doi: 10.1109/IISEC56263.2022.9998211.

Imani, M., & Arabnia, H. R. (2023). Hyperparameter Optimization and Combined Data Sampling Techniques In Machine Learning For Customer Churn Prediction: A Comparative Analysis. Technologies, 11(6), 167. https://doi.org/10.3390/technologies11060167

Feroz, S. B., Sharmin, N., & Sevas, M. S. (2024). An Empirical Analysis Of Hyperparameter Tuning Impact On Ensemble Machine Learning Algorithm For Earthquake Damage Prediction. Asian Journal of Civil Engineering, 25(4), 3521–3547.




DOI: https://doi.org/10.17509/coelite.v4i1.81020

Refbacks

  • There are currently no refbacks.


Journal of Computer Engineering, Electronics and Information Technology (COELITE)


is published by UNIVERSITAS PENDIDIKAN INDONESIA (UPI),
and managed by Department of Computer Enginering.
Jl. Dr. Setiabudi No.229, Kota Bandung, Indonesia - 40154
email: coelite@upi.edu
e-ISSN: 2829-4149
p-ISSN: 2829-4157