Customising generative AI: Harnessing document retrieval and fine-tuning alternatives for dynamic marketing insights
Abstract
This study delves into the transformative impact of leveraging large language models (LLMs) in marketing analytics, particularly emphasising a paradigm shift from fine-tuning models to the strategic application of document retrieval techniques and more. Focusing on innovative methods, such as retrieval augmented generation and low-rank adaptation, the paper explores how marketers can now activate against vast and unstructured datasets, such as call centre transcripts, unlocking valuable insights that were previously overlooked. By harnessing the power of document retrieval and adaptation, marketers can bring their data to life, enabling a more nuanced and adaptive approach to understanding consumer behaviour and preferences. This research contributes to the evolving landscape of applied marketing analytics by demonstrating the efficacy of document retrieval in enhancing the utilisation of LLMs for dynamic and data-driven marketing strategies.
The full article is available to subscribers to the journal.
Author's Biography
Dakota Crisp is a senior manager of data science at OneMagnify. With a PhD from the University of Michigan, his hypothesis-driven approach to investigating complex systems provides a distinctive take on consumer behaviours. Dakota is an exceptionally skilled writer who leads many of OneMagnify's internal and external publications. His passion for leadership enables his team to transform marketing analytics into innovative solutions.
Jacob Newsted a data engineer and data scientist at OneMagnify, boasts a multifaceted background in computer science. His expertise spans an impressive array of disciplines, including game development, web development, data engineering and data science. This diversity enables him to approach various problem spaces with unique perspectives. Jacob earned his MS in machine learning and evolutionary computation from Michigan State University. He is passionately committed to continuous learning and applying cutting-edge advancements in these fields to his work.
Brendon Kirouac is a data scientist at OneMagnify. He earned his BS in physics from Wayne State University and shortly after began work in L4 autonomous vehicle development as a systems and integration test engineer focused on motion planning and controls. Observing the ability of machine learning to enable a vehicle to perceive and navigate the world inspired him to pursue data science. At OneMagnify, Brendon is working on designing and implementing consumer-facing end-to-end generative AI solutions.
Danielle Barnes is a senior director of data science at OneMagnify. She is an accomplished analytics leader with extensive experience across the entire data life cycle. Her work directing enterprise analytics initiatives for companies across various industries has made her a powerhouse at realising visions in complex environments. She is a Spartan superfan with a BA in mathematics and an MS in statistics, and she is currently pursuing a PhD in data science, all from Michigan State University.
Catherine Hayes is a senior director of IT at OneMagnify. Her experiences as a full-stack engineer, small business owner, teacher and technology leader have contributed to her exceptional ability to help break down abstract technical concepts and translate client requirements into functional and elegant solutions. She leads a team of data engineers, software developers and solution architects.
Jonathan Prantner is the Chief Analytics Officer at OneMagnify. His approach to applied mathematics has pushed analytics to the limits for over two decades. Jonathan's career has spanned educational research, automotive, consumer packaged goods, travel and healthcare. At OneMagnify, he leads efforts surrounding applied artificial intelligence and machine learning as well as integrating advanced analytics with data visualisation platforms. Jonathan is a celebrated thought leader and the recipient of multiple data science patents.
Citation
Crisp, Dakota, Newsted, Jacob, Kirouac, Brendon, Barnes, Danielle, Hayes, Catherine and Prantner, Jonathan (2024, June 1). Customising generative AI: Harnessing document retrieval and fine-tuning alternatives for dynamic marketing insights. In the Applied Marketing Analytics: The Peer-Reviewed Journal, Volume 10, Issue 1. https://doi.org/10.69554/YBXQ5617.
Publications LLP