Amazon is using artificial intelligence (AI) to better understand search queries and why a person may be looking for something.

Understanding why a customer searches for a product is just as import as knowing what they searched for. Knowing the context can help a retailer make relevant recommendations for other products that not only compliment the item being searched for, but the activity or reason behind the search. Amazon is intent on cracking that piece of the puzzle, and is applying AI to the problem.

“In a paper accepted to the ACM SIGIR Conference on Human Information Interaction and Retrieval, my colleagues and I present a new neural-network-based system for predicting context of use from customer queries,” writes Adrian Boteanu. “From the query ‘adidas mens pants’, for instance, the system predicts the activity ‘running.’

“In tests, human reviewers agreed, on average, with 81% of the system’s predictions, indicating that the system was identifying patterns that could improve the quality of Amazon’s product discovery algorithms.”

As Amazon continues to improve its algorithms, shoppers should see increasingly relevant shopping recommendations and the research could open a whole new arena for personalized digital shopping assistants.