Voice of the customer is traditionally captured using feedback from sales channels which is generally reviews. While consolidating product reviews has been done in a semi-automated fashion with the help of summarization, segmentation and subject matter expertise, it is always a time taking and resource intensive process that spans multiple cycles of rework.
Here at DataRobot, we aim to use our Generative AI Solution framework to build an automated system to process review text and use Generative AI to produce targeted reports for product design and manufacturing teams.
Product teams go through the exercise of defining their development roadmap based on the voice of the customer.
About this Accelerator
This accelerator shows how to use Predictive AI models in tandem with Generative AI models and overcome the limitation of guardrails around automating summarization/segmentation of sentiment text. In a nutshell, it consumes product reviews and ratings and outputs a Design Improvement Report.
What you will learn
Extract high impact review keywords from product reviews using DataRobot.
During keyword extraction, implement guardrails for selecting models with higher AUC to make sure keywords are robust and correlated to the review sentiment.
Generate product development recommendations for the final report.