Optimising Digital Advertising Using Generative AI: A Design Science Approach to Keyword Generation and Decision Support

Syed Farhan and Colin Fu ()
Additional contact information
Syed Farhan: University of Surrey
Colin Fu: University College London

A chapter in Advanced Data Analytics, Machine Learning and AI in Business, 2026, pp 330-358 from Springer

Abstract: Abstract This study presents a design science artefact that operationalises the Cognitive AI Framework (Fu and Ioannou, 2025) to enhance digital advertising decision-making. By integrating generative models (BART, GPT-3.5) with predictive analytics (Random Forest), the system moves beyond content creation to prescribe optimal keyword allocation based on predicted click-through rates (CTR). Using the Cognitive AI stages of Engage (generation), Examine (prediction), and Formulate (decision), the system demonstrates how AI tools can function as prescriptive decision support systems rather than mere creative assistants. Empirical findings show transformer-based models significantly outperform traditional LSTM in accuracy, while the predictive layer acts as a governance gate for campaign planning. A locally deployable prototype with voice input via Whispr illustrates how such a framework functions in applied contexts. Conceptually, we identify five affordances, i.e. creative scalability, performance-aware prescription, multimodal interaction, domain portability, and transparency that enable marketers to transition from descriptive analytics to prescriptive action. These insights extend recent work on AI-enabled advertising (Singh et al., 2024; Korst et al., 2025) and provide a blueprint for experimental adoption.

Keywords: Generative Artificial Intelligence; Prescriptive Analytics; Cognitive AI Framework; Digital Advertising; Decision Support Systems (search for similar items in EconPapers)
Date: 2026
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:spr:lnopch:978-3-032-23493-3_21

Ordering information: This item can be ordered from
http://www.springer.com/9783032234933

DOI: 10.1007/978-3-032-23493-3_21

Access Statistics for this chapter

More chapters in Lecture Notes in Operations Research from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().