Wayfair introduces new technology that combines ML and AI to make search results more accurate

It is learned that on May 30, according to foreign media reports, American home furnishing giant Wayfair is using ML (machine learning technology) and SnorkelAI to automate large-scale data labeling, build a model based on product features, and provide customers with more accurate search results.

SnorkelAI is an open source software tool for data annotation and training machine learning models, which can reduce the cost and time of training data labeling. ML technology trains models to identify patterns and regularities in data and use these models to make predictions, decisions or perform specific tasks.

Tulia Plumettaz, head of machine learning at Wayfair, said that through the application of new technologies, customers can find the products they want more easily, which means that conversion rates and customer satisfaction will be significantly improved. At the same time, the model built based on product features will help Wayfair to change and enrich the product catalog in a timely manner according to market trends more quickly.

At first, Wayfair considered that the platform has thousands of products, each of which has rich information and product features. So, is it possible to use this information to build a model based on certain product features, such as the color, texture, and armrest shape of a sofa? Customers can search based on these detailed features and find the products they want.

Building these models requires a large amount of training data, and Wayfair hopes to minimize the amount of information collected from sellers. The role of SnorkelAI is to use automated methods to quickly and accurately label data and provide labeled data samples for training models.

Data labeling is a critical step in machine learning, and SnorkelAI provides Wayfair with a more efficient, flexible, and scalable way to build and train models by programmatically labeling images for Wayfair.

The collaboration will also be used to adjust and enrich Wayfair's product catalog. Plumettaz said that programmatic data annotation technology allows Wayfair professionals to easily create new product categories and ensure that the correct images are provided to consumers. When new trends emerge in the home decor field, professionals will be able to make changes to the product catalog more easily.

Prior to this, Wayfair mainly processed 40 million products manually and tried to label them, so from a business perspective, this is a real value release. ML technology has been widely used in the e-commerce field, and through the combination of SnorkelAI, this technology will play a greater role.

Editor✎ Ashley/

Disclaimer: This article is copyrighted and may not be reproduced without permission.