Copastur is a consulting services and resource management company for corporate trips, leisure, and events with 50 years of history.
The complexity in evaluating different flight options led to overvaluation of small cost differences, and Copastur faced limitations with airline fares, unable to influence customers to opt for potentially more profitable ones even when they are more suitable for the user and have reduced cost variation.
Developing a personalized LLM-powered model to determine the ideal fares in airline ticket purchase requests.
AI/R Compass UOL, in partnership with AWS, developed a customized model to determine optimal fares for airline ticket purchase requests using airline information, historical transactional data, and personalized LLM to contextualize recommendations and enable Copastur to offer personalized and informative suggestions according to the specific needs of each client.
We leveraged Amazon SageMaker to create the customized model and Amazon Bedrock to restrict recommendations via prompt, ensuring a more contextualized and humanized approach.
Data integration was carried out using AWS Glue with storage in Amazon S3, and the resulting recommendations were stored in Amazon S3 and consumed via AWS Lambda Functions for the Amazon API Gateway.
The complete infrastructure was created via AWS CloudFormation, providing access to Amazon SageMaker Studio for the data scientists involved, delivering a flexible structure that can be adapted to different projects.
Recommendation for the most advantageous rate, improving experience and optimizing profits even in situations where the tariff is not the lowest
Improved conversion rate and user satisfaction with intelligent, personalized recommendations
Increased average fare with higher costs but greater convenience for users
Reduced search abandonment with greater efficiency in users' ability to find what they are looking for
Read other stories
PagueMenos
Brazil’s second largest pharmacy chain uses AI & ML to personalize product ranking and experiences
Compre & Alugue Agora
Brazil’s first and only social media for Real Estate reduces chatbot costs by 80% and improves responses with AI