MaxAB
Revolutionising pricing algorithms with AWS and GenAI.
Credera was engaged by MaxAB to update their existing pricing algorithm and transform data querying with Generative AI.
At a Glance
Leading B2B e-commerce platform MaxAB wanted to update their existing pricing algorithm to maximise business KPIs.They partnered with Credera to enhance their pricing strategies and customer interaction capabilities using cutting-edge AI technologies, leveraging AWS Sagemaker and Sagemaker Jumpstart to optimise their existing pricing algorithm and lay the groundwork for a reinforcement learning model.
The Challenge
Updating a legacy pricing algorithm.
MaxAB wanted to update their existing pricing algorithm to maximise business KPIs, whilst reducing training time. They also wanted to demonstrate how reinforcement learning and GenAI could be utilised in a complex market environment.
The Solution
Enhancing model performance and efficiency.
We conducted Exploratory Data Analysis to reduce 30 features in the MaxAB data set to the top four predictors of future prices. Additionally, we created the reward function, pricing model, policy guidelines, and testing environment for a reinforcement learning algorithm. Finally, we built a chatbot enabling non-technical users to ask pricing questions and receive 100% accurate responses from their own dataset.
The Results
Improved predictive accuracy and training efficiency.
By implementing feature engineering and model simplification, we were able to reduce over 30 features to the top predictors of price, thereby decreasing overall complexity and improving predictability (R2: 0.7-0.8). Additionally, we demonstrated that simplified regression models could reduce training time by up to 15x, with deployment to production pending.
Contact Us
Ready to achieve your vision? We're here to help.
We'd love to start a conversation. Fill out the form and we'll connect you with the right person.
Searching for a new career?
View job openings
