In the airline industry, information is often dispersed across a variety of departments, from airlines operations and maintenance to staff management and customer service. This can lead to the creation of inadvertent silos that make it challenging to quickly synthesize information company wide. In United’s case, staff from all departments still rely on manually searching through multiple internal platforms to find information, which not only slows decision making but also increases the risk of inconsistencies across the organization.
This paper presents an intelligent assistant for United Airlines that leverages a fine-tuned Retrieval-Augmented Generation (RAG) architecture to support a wide range of information retrieval tasks, showcased by a specific application for gate agent customer service. Ultimately, the intelligent assistant consolidates information from a variety of internal customer service and operations documents (including, but not limited to United.com, Wingtips, Flying Together, and SkySupport), enabling unified and precise knowledge retrieval across organizational sources.
The latest version of the intelligent assistant further leverages knowledge distillation using Small Language Models (SLMs) to operate efficiently in offline environments, such as mobile devices and self-service kiosks. Preliminary results demonstrate that the fine-tuned RAG model achieves strong retrieval accuracy and high response quality, while the distilled RAG model further reduces computational requirements without compromising performance. Together, these results highlight a novel pipeline capable of driving company-wide improvements in information flow, workflow efficiency, and operational effectiveness.
Watch the team present this project at 01:19:22 in the session recording here.
Keywords: Artificial Intelligence (AI), Natural Language Processing (NLP), Retrieval-Augmented Generation, Knowledge Distillation, Airline Operations, Chatbot, Customer Service Automation
Faculty Advisors
Dr. Pamuksuz, a professor of AI, specializes in applied mathematics, machine/deep learning, responsible and generative AI. He has contributed to various analytics journals, including IEEE Transactions on Artificial Intelligence, and has shared his insights at several national and international conferences.
Since joining the University of Chicago as a faculty member in 2018, Dr. Pamuksuz has taught a range of subjects, including data mining, machine learning, and linear & non-linear models, along with more specialized areas like AI-data science for leaders and Generative AI Research. His supervision of capstone theses has often centered on computer vision and natural language processing.
In the professional realm, Dr. Pamuksuz has an impressive record. He has led data science teams at several Fortune 500 companies, provided expert consultancy in architecting cloud-based machine learning solutions, and co-founded Inference Analytics in 2018. Under his leadership, Inference Analytics was recognized in 2023 as one of the top Machine Learning Companies in Illinois, marking a significant milestone in healthcare analytics in Chicago.
Dr. Pamuksuz’s academic path has taken him through some of Illinois’ most prestigious universities. He completed his MS in Computer Engineering/Science at Northwestern University and went on to earn his Ph.D. from UIUC. Today, he contributes his expertise as a faculty member at the University of Chicago. This journey, connecting three significant academic institutions, reflects a strong foundation and dedication to his field and a deep engagement with the state’s rich educational landscape. Outside of his professional endeavors, Dr. Pamuksuz is enthusiastic about hackathons, not only participating in several but also organizing them twice annually since 2020. His involvement has yielded notable success in various data challenges. As a sports fan, he follows Champions League Soccer, supporting Galatasaray, and enjoys engaging in basketball and volleyball during his leisure time. He also enjoys smooth/gypsy jazz where you can find him on Wednesdays in his favorite place Green Mill.