SalesTech Star

Particular Audience Unveils Revolutionary ‘Adaptive Transformer Search’ Solving the $300 Billion eCommerce Search Problem

Particular Audience Unveils Revolutionary 'Adaptive Transformer Search'  Solving the $300 Billion eCommerce Search Problem | Business Wire

Brand new AI-powered site search understands shopper intent, capable of reducing zero-search results by up to 70%.

Particular Audience, a pioneer in advanced artificial intelligence technologies for ecommerce, today announced the launch of its revolutionary Adaptive Transformer Search (ATS). This AI-powered search technology promises to solve the underlying problems plaguing ecommerce search as reported by 94% of consumers, representing a significant leap forward in search efficiency and customer experience.

“Large Language Models are generating a lot of buzz, and we are proud to be at the forefront of AI in ecommerce with the introduction of Adaptive Transformer Search”

Discovery on the Internet has come to rely on search and recommendation technologies for fast and intuitive information retrieval. While legacy keyword search has worked well enough, it still suffers from inherent flaws associated with exact word matching and a tangle of rules that need constant management. These issues are exacerbated by messy and/or incorrect metadata in a retail website’s product feed. The cost of this problem is estimated by Google to be worth $300bn per annum in the USA alone.

76% of customers report they abandon a retailer after failing to find what they are searching for, with 48% then purchasing the item elsewhere. More than half report they typically abandon their entire shopping cart after failing to find a single item on a website. Eighty-five percent of consumers say they view a brand differently after experiencing search difficulties and 77% avoid websites where they’ve had poor search experiences. Customers are not alone in acknowledging the extensive problem of bad site search; retailers agree, 90% of US based website managers surveyed are concerned about the cost of search abandonment to their business, while more than half have no clear plan for improvement.

Unlike conventional ecommerce search engines that rely on exact keyword matching and continuous manual updates, ATS is designed to understand the meaning and context of words in a query. This innovative approach eliminates the need for extensive manual configuration, reducing overhead for website owners and facilitating an intuitive search experience for customers. Longtail search queries can make up to 80% of site search and this is one of the key opportunities that ATS is best placed to solve.

“At Particular Audience, we’ve always focused on addressing the root causes of discovery abandonment with applied artificial intelligence,” said CEO, James Taylor. “With ATS, we’ve harnessed the power of Large Language Models, paired with our own vertical tuning to generate the most relevant search results right out of the box. No matter how niche or conversational a search is.”

Read More: Auctane Appoints Albert Ko As CEO

Adaptive Transformer Search is built using transformer models, converting sequential long form text (retailer catalogue and website data) into vectors in high-dimensional space. The conversion of a sequence of words into a vector is known as sentence embeddings, a concept popularised by large language models such as Google’s BERT and OpenAI’s GPT. This means ATS is capable of understanding the meaning in a sentence and can, for example, understand the difference between ‘getting a laptop online using a credit card’, and ‘getting a credit card online using a laptop’.

Adaptive Transformer Search leverages PA’s proprietary Vertical Tuned Models (VTMs), creating sentence embeddings that adapt from localized reinforcement learning. This continual learning process enables ATS to improve its precision and accuracy specific to individual retailer websites.

“Automating the tuning of search results through ‘query-click-pair’ reinforcement learning has been a game changer for our ATS product. What this means in simple terms is that our models continually learn from user search queries, understanding context to optimise results for future queries. Adapting search relevance in real-time to evolving consumer context has never been possible on retailer websites before now,” said Particular Audience’s Head of Product, Patrick DiLoreto.

Read More: SalesTechStar Interview with John Serdinsky, Chief Customer Officer at Pramata

The positive impact of ATS on an ecommerce website is profound. It increases search revenue by more than 20% when compared with legacy keyword search technology, it reduces the instance of zero-search-results by as much as 70%, and enhances customer engagement through better ranking of results. This breakthrough technology is purpose-built to facilitate intuitive and efficient search experiences for every customer, ensuring that they find what they are looking for every time they shop.

“Large Language Models are generating a lot of buzz, and we are proud to be at the forefront of AI in ecommerce with the introduction of Adaptive Transformer Search,” added CEO, James Taylor. “We believe this revolutionary technology will not only transform the way consumers shop online but also set a new standard for search efficiency and customer experience in the ecommerce industry.”

Write in to psen@itechseries.com to learn more about our exclusive editorial packages and programs.

Brought to you by
For Sales, write to: contact@martechseries.com
Copyright © 2024- SalesTechStar. All Rights Reserved. Website Design:SalesTechStar | Privacy Policy
To repurpose or use any of the content or material on this and our sister sites, explicit written permission needs to be sought.