Amazon’s AI predicts product quality from customer feedback
Amazon scientists are prototyping algorithms that use crowdsourcing to identify product data, the company reports in a blog post. The researchers believe they could be used to predict human judgments of product quality on Amazon, which might improve customers’ shopping experiences by matching only high-quality products to search queries.
The work is something of a follow-up to a study Amazon published in early January, which examined why Amazon customers buy seemingly irrelevant products while shopping for specific things. In an analysis, a team of Amazon researchers found that customers are partial to products that are broadly popular or cheaper than products relevant to a given search query. Additionally, their results suggested that people are more likely to buy or engage with irrelevant products in a few categories — such as toys and digital products — than in categories like beauty products and groceries.
In this latest study, which is scheduled to be presented next week at the ACM SIGIR Conference on Human Information Interaction and Retrieval (CHIIR) in Vancouver, the researchers presented crowd workers with images of pairs of related products together with product information supplied by both sellers and customers. They asked them which products were of higher quality, and then they asked them which terms extracted from the product information best explained their judgments.
Each product pair in the study included (1) one product that was actually purchased and (2) one that was clicked on but not purchased during the same customer search query. Products also shared the most fine-grained classification available in the Amazon.com product classification hierarchy (e.g., “Electronics,” “Home,” “Kitchen,” “Beauty,” “Office Products”), and the terms presented to the crowd workers were chosen based on how frequently they appeared in texts associated with those fine-grained categories.
The team found that while perceived quality wasn’t a good predictor of customers’ purchase decisions, it was highly correlated with price, such that customers generally chose lower-quality products if they were correspondingly lower-priced. Furthermore, the terms that best described the crowd workers’ judgment criteria came from the public customer-supplied information — that is, customer reviews and question-and-answer sequences in which customers answered other customers’ product-related questions — as opposed to the seller information.
“Existing research on product recommendation has mainly focused on modeling purchases directly, without attempting to find the reasons behind customer decisions. We believe that understanding the processes that underlie customers’ purchasing decisions will help us make better product recommendations,” wrote study coauthors Jie Yang, Rongting Zhang, and Vanessa Murdock. “This work represents one of several steps we’re taking in that direction.”
Source: Read Full Article