Amazon’s AI Product Platform Helps You Shop Smarter

Agrawal is an engineering chief at Amazon Web Services in Seattle. An knowledgeable in AI and machine learning, the IEEE senior member labored on Microsoft’s Bing search engine earlier than transferring to Amazon. He additionally developed a number of options for Microsoft Teams, the corporate’s direct messaging platform.

“I’ve been working in AI for greater than 20 years now,” he says. ”Seeing how a lot we are able to do with know-how nonetheless amazes me.”

He shares his experience and fervour for the know-how as an lively member and volunteer on the IEEE Seattle Section. He organizes and hosts profession growth workshops that educate folks to create an AI agent, which might carry out duties autonomously with minimal human oversight.

An AI profession impressed by a pc

Agrawal was born and raised in Chirgaon, a distant village in Uttar Pradesh, India. When he was rising up, nobody in Chirgaon had a pc. His household owned a pharmacy, which Agrawal was anticipated to hitch after he graduated from highschool. As a substitute, his uncle and older brother inspired him to attend faculty and discover his personal ardour.

He loved mathematics and physics, and he determined to pursue a bachelor’s diploma in statistics on the University of Allahabad. After graduating in 1996, he pursued a grasp’s diploma in statistics, statistical high quality management, and operations analysis on the Indian Statistical Institute in Kolkata.

Whereas on the ISI, he noticed a pc for the primary time within the laboratory of Nikhil R. Pal, an electronics and communication sciences professor. Pal labored on figuring out irregular clumps of cells in mammogram photographs utilizing the fuzzy c-means model, a data-clustering approach using a machine studying algorithm.

Agrawal earned his grasp’s diploma in 1998. He was so impressed by Pal’s work, he says, that he stayed on on the college to earn a second grasp’s diploma, in laptop science.

After graduating in 2001, he joined Novell as a senior software program engineer understanding of its Bengaluru workplace in India. He helped develop iFolder, a storage platform that enables customers throughout completely different computer systems to again up, entry, and handle their recordsdata.

After 4 years, Agrawal left Novell to hitch Microsoft as a software program design engineer, working on the firm’s Hyderabad campus in India. He was a part of a workforce creating a system to improve Microsoft’s software program from XP to Vista.

Two years later, he was transferred to the group creating Bing, a alternative for Microsoft’s Dwell Search, which had been launched in 2006.

Enhancing Microsoft’s search engine

Dwell Search had a site visitors charge of lower than 2 % and struggled to maintain up with Google’s faster-paced, extra user-friendly system, Agrawal says. He was tasked with bettering search outcomes however, Agrawal says, he and his workforce didn’t have sufficient person search knowledge to coach their machine studying mannequin.

Information for location-specific queries, resembling close by espresso retailers or eating places, was particularly necessary, he says.

To beat these challenges, the workforce used deterministic algorithms to create a extra structured search. Such algorithms give the identical solutions for any question that makes use of the identical particular phrases. The method will get outcomes by taking key phrases—resembling places, dates, and costs—and discovering them on webpages. To assist the search engine perceive what customers want, Agrawal developed a question clarifier that requested them to refine their search. The machine studying device then ranked the outcomes from most to least related.

To check new options earlier than they had been launched, Agrawal and his workforce constructed a web based A/B experimentation platform. Managed exams had been accomplished on completely different variations of the merchandise, and the platform ran efficiency and person engagement metrics, then it produced a scorecard to indicate modifications for up to date options.

Bing launched in 2009 and is now the world’s second-largest search engine, in keeping with Black Raven.

All through his 10 years of engaged on the system, Agrawal upgraded it. He additionally labored with the promoting division to enhance Microsoft’s companies on Bing. Advertisements related to an individual’s search are listed among the many search outcomes.

“The work appears straightforward,” Agrawal says, “however behind each search engine are a whole bunch of engineers powering advertisements, question formulations, rankings, relevance, and placement detection.”

Testing merchandise earlier than launch

Agrawal was promoted to software development supervisor in 2010. 5 years later he was transferred to Microsoft’s Seattle workplaces. On the time, the corporate was deploying new options for current platforms with out first testing them to make sure effectiveness. As a substitute, they measured their efficiency after launch, Agrawal says, and that was wreaking havoc.

He proposed utilizing his on-line A/B experimentation platform on all Microsoft merchandise, not simply Bing. His supervisor accredited the thought. In six months Agrawal and his workforce modified the device for company-wide use. Because of the platform, he says, Microsoft was capable of easily deploy up-to-date merchandise to customers.

After one other two years, he was promoted to principal engineering supervisor of Microsoft Groups, which was dealing with points with user experience, he says.

“Many workers acquired between 50 and 100 messages a day—which grew to become overwhelming for them,” Agrawal says. To minimize the stress, he led a workforce that developed the system’s first machine studying function: Trending. It prioritized the 5 most necessary messages customers ought to give attention to. Agrawal additionally led the launch of incorporating emoji reactions, display sharing, and video requires Groups.

In 2020 he was prepared for brand spanking new experiences, he says, and he left Microsoft to hitch Amazon as an engineering chief.

Improved Amazon buying

Agrawal led an Amazon workforce that manually collected details about merchandise from the corporate’s retail catalog to create a glossary. The information, which included product dimensions, colour, and producer, was used to standardize the language present in product descriptions to maintain listings extra constant.

That’s particularly necessary relating to third-party sellers, he notes. Sellers itemizing a product had been coming into as a lot or as little info as they wished. Agrawal constructed a system that robotically suggests language from the glossary as the vendor sorts.

He additionally developed an AI algorithm that makes use of the glossary’s terminology to refine search outcomes primarily based on what a person sorts into the search bar. When a consumer sorts “pink mixer,” for instance, the algorithm lists merchandise beneath the search bar that match the outline. The patron can then click on on a product from the checklist.

In 2023 the retailer’s catalog grew to become too giant for Agrawal and his workforce to gather info manually, so that they constructed an AI device to do it for them. It grew to become the muse for Amazon’s Catalog AI system.

After gathering details about merchandise from across the Net, Catalog AI makes use of large language models to replace Amazon listings with lacking info, appropriate errors, and rewrite titles and product specs to make them clearer for the client, Agrawal says.

The corporate expects the AI device to extend gross sales this 12 months by US $7.5 billion, in keeping with a Fox News report in July.

Discovering objective at IEEE

Since Agrawal joined IEEE final December, he has been elevated to senior member and has develop into an lively volunteer.

“Being a part of IEEE has opened doorways for collaboration, mentorship, {and professional} progress,” he says. “IEEE has strengthened each my technical data and my management abilities, serving to me progress in my profession.”

Agrawal is the social media chair of the IEEE Seattle Part. He’s additionally vice chair of the IEEE Computational Intelligence Society.

He was a workshop cochair for the IEEE New Era AI World Leaders Summit, which was held from 5 to 7 December in Seattle. The occasion introduced collectively authorities and trade leaders, in addition to researchers and innovators engaged on AI, clever gadgets, unmanned aerial vehicles, and comparable applied sciences. They explored how new instruments may very well be utilized in cybersecurity, the medical discipline, and nationwide disaster rescue missions.

Agrawal says he stays updated on cutting-edge applied sciences by peer-reviewing 15 IEEE journals.

“The group performs a vital function in bringing authenticity to something that it does,” he says. “If a journal article has the IEEE emblem, you possibly can imagine that it was thoroughly and diligently reviewed.”