Solution Accelerator
Building Common Sense Product Recommendations With LLMs
Pre-built code, sample data and step-by-step instructions ready to go in a Databricks Notebook
Deliver intuitive product recommendations that drive customer journeys
Product recommendations play a central role in guiding customers through their shopping journey with tailored suggestions based on their buying behaviors and preferences. With large language models (LLMs), retailers can automate the delivery of personalized suggestions that adapt to evolving customer preferences — enhancing user engagement, increasing sales and fostering long-term customer loyalty.
Use this Solution Accelerator to develop product recommendations based on common sense linkages for new-to-market products and optimized recommendation engines:
- Convert all of your specific product descriptions and metadata into embeddings and store them in a searchable index
- Task an LLM to recommend products based on their connection to other relevant products
Resources
Blog
Commonsense Product Recommendations Using Large Language Models
Blog
Retail in the Age of Generative AI
10 ways large language models (LLMs) may impact the retail industry
Blog
Fine-Tuning Large Language Models With Hugging Face and DeepSpeed
Easily apply and customize large language models of billions of parameters