Decoding Consumer Behaviour: Leveraging Big Data and Machine Learning for Personalized Digital Marketing

Anber Abraheem Shlash Mohammad, Suleiman Ibrahim Shelash Mohammad, Badrea Al Oraini, Ayman Hindieh Ayman Hindieh, Asokan Vasudevan Asokan Vasudevan and Muhammad Turki Alshurideh

Data and Metadata, 2025, vol. 4, 700

Abstract: Introduction Big data analytics and machine learning have transformed digital marketing by enabling data-driven insights for personalization. This study investigates the role of engagement metrics, sentiment analysis, and consumer segmentation in enhancing marketing effectiveness. Specifically, it examines how these technologies process consumer interaction data to uncover actionable insights, segment audiences, and drive purchase conversions. Method The study employed a mixed-methods approach, integrating big data analytics and machine learning techniques. Descriptive statistics highlighted engagement patterns, while k-means clustering segmented consumers based on behavioural and emotional data. Sentiment analysis, conducted using Natural Language Processing (NLP), captured consumer emotions as positive, neutral, or negative. Regression analysis evaluated the influence of social media activity, click-through rates, session duration, and sentiment scores on purchase conversion rates. Results Descriptive analysis revealed significant variability in consumer engagement and sentiment, with 37.5% of consumers expressing positive sentiment. Clustering identified three distinct consumer segments, reflecting differences in engagement and sentiment. Regression analysis showed that sentiment had a positive but statistically insignificant relationship with purchase conversions, while other metrics, such as click-through rates and session duration, exhibited minimal impact. The overall explanatory power of the regression model was low (R-squared = 0.001), indicating the need for additional factors to understand purchase behaviour. Conclusion The findings emphasize the potential of big data analytics and machine learning in consumer segmentation and sentiment analysis. However, their direct impact on purchase conversion is limited without integrating broader variables. A holistic, adaptive framework combining behavioural, emotional, and contextual insights is essential for maximizing marketing personalization and driving outcomes in dynamic digital environments.

Date: 2025
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:dbk:datame:v:4:y:2025:i::p:700:id:1056294dm2025700

DOI: 10.56294/dm2025700

Access Statistics for this article

More articles in Data and Metadata from AG Editor
Bibliographic data for series maintained by Javier Gonzalez-Argote ().