Startup of the week | ExpertRec – Disrupting search and recommendation using Machine learning

Design by Team ExpertRec

Team ExpertRec

The e-commerce sites invest a lot of money in bringing traffic to their sites through various means such as- AdWords, SEO & SEM but they miss on is the onsite conversion optimisation. Once a user lands onto a website, there are two main channels for the discovery- Search and Product Recommendations. And the effectiveness of onsite conversion depends largely on speed, relevance and personalisation levels of these search and recommendation engines. This is the reason why global giants like Google, Amazon invest heavily on Machine Learning and AI technologies to up their “search” game.

Why do we bring this discussion here? Well, delivering upon an unmatchable search experience is ExpertRec, an India based startup,  whose plug and play search engine with best in class machine learning capabilities never fail to ‘wow ‘customers. Founded by ex-Googler, Melchizedec Sundararaj in 2013, he brings his experience on large scale machine translation on the table, while bringing advanced search and rec technologies to SMB and other small ecommerces.

How Search at ExpertRec works?

Advanced AI and machine learning algorithm at ExpertRec-

With a vision to enable every e-commerce into using cutting edge technologies in search and product recommendation, ExpertRec is relying on advanced artificial intelligence and machine learning algorithms. The intelligent search by ExpertRec lets the user find products relevant to their personal tastes and needs. Their machine learning algorithms learn from user behaviour and re-ranks results to optimize the user experience.  

Subscribe to our Newsletter

Join our editors every weekday evening as they steer you through the most significant news of the day, introduce you to fresh perspectives, and provide unexpected moments of joy
Your newsletter subscriptions are subject to AIM Privacy Policy and Terms and Conditions.

All of ExpertRec’s products are built on a big data processing platform Cloudbash that can scale effortlessly to petabytes of data, mirroring Google’s infrastructure and the technology best practices. It thus enables ecommerce to go live with an ultra fast search and recommendation engine in a matter of seconds. As the company says, There is no need to manually tune search relevance or worry about speed. Just include our JavaScript and let the machines do their magic.”

How it learns from user behaviour?

ExpertRec’s search engine allows a user to just click and go live, without a need of technical expertise. Advanced users and developers can also use API’s to integrate on mobile & web, and customize the search experience according to their customer requirements.

It comes with various interesting features where it learns from the user behaviour. Its spell correction function being the utmost one. It can easily fix typing errors and display suggestions for correct keyword. For instance, while typing Britney Spears, there are thousands of spelling errors that can be made while typing. The machine learning capabilities by ExpertRec can identify each of these spelling errors and still lead you to the desired results.

t can easily fix typing errors and display suggestions for correct keyword

As the company believes When you are dealing with massive data sets, and a huge search customer base, putting in a machine learning system that can learn from a user behaviour is the most optimal way of delivering a relevant search experience for every user”. Expertrec uses around 65 parameters to make sure every user gets personalised search results that reflects his actual intent.

One of the other advantages of ExpertRec’s machine learning algorithms is that it can easily figure out Natural Language Processing queries, where most of the other search engine falter. For instance, a search query like “shirts lesser than 2000” might not give results on other search engines but ExpertRec handles this beautifully with its advanced deep learning algorithms. This is available in the enterprise edition for sites that have large traffic.

Speed matters-

Melchizedec Sundararaj, Founder, ExpertRec

Amazon reportedly loses 1 % in sales for every 100ms of latency, Google traffic drops by 20% for an extra 0.5 seconds in search page loading time. So it is important for every e-commerce to reduce the time between user landing on a page and the product bought by them. ExpertRec search latency on the server side is lesser than a millisecond. With Expertrec you can be sure that you are delivering the world’s fastest search experience”, says Sundararaj, Founder, ExpertRec.

One of the key factors that increases the engagement with the onsite search engine is the UI of the search box. We have found that, every business needs a custom UI. Once a user signs up, they can get creative and design their own search UI that they think will resonates well with their user”, adds Sundararaj.

Search analytics and adding business logic to search-

“With Expertrec’s real time analytics you can actually get into the minds of your users”, says Sundararaj. Getting insights on top searched queries, queries that ended in zero product result, the places where crowd dropped off are some of the things that ExpertRec allows. The user can also perform various AB tests and monitor the impact on sales and revenue through the search analytics dashboard.

It can also add business logic to search. Most business leaders have accumulated a lot of business intelligence and knowledge in their own domains. This knowledge can be used to augment the learning that ExpertRec’s machines do. Using the control panel, user can add the domain knowledge easily.

Automating Effective upselling and cross selling-

ExpertRec comes with a powerful recommendation engine which allows customer to find his product effortlessly. Apart from predicting the products that customer is looking it, it also keeps updating recommendations till he finds the product.

It’s the collaborative-filtering algorithm, which is being used here that keeps the customer experience outstanding. The built in recommendation engine allows implementing algorithms such as “customers who viewed this also viewed”, “bought also bought”, “frequently bought together” etc., really fast. User can build their own custom recommendation engines applying their own business rules and logics.

Currently top e-commerce companies across the globe including Aditya Birla group, are leveraging ExpertRec’s unique technology to gain an upper hand in the this cut-throat competition. Other customers include Allen Solly, VanHeusen, Peter England etc.

To use ExpertRec’s search engine technology, visit

Srishti Deoras
Srishti currently works as Associate Editor at Analytics India Magazine. When not covering the analytics news, editing and writing articles, she could be found reading or capturing thoughts into pictures.

Download our Mobile App


AI Hackathons, Coding & Learning

Host Hackathons & Recruit Great Data Talent!

AIM Research

Pioneering advanced AI market research

Request Customised Insights & Surveys for the AI Industry


Strengthen Critical AI Skills with Trusted Corporate AI Training

Our customized corporate training program on Generative AI provides a unique opportunity to empower, retain, and advance your talent.

AIM Leaders Council

World’s Biggest Community Exclusively For Senior Executives In Data Science And Analytics.

3 Ways to Join our Community

Telegram group

Discover special offers, top stories, upcoming events, and more.

Discord Server

Stay Connected with a larger ecosystem of data science and ML Professionals

Subscribe to our Daily newsletter

Get our daily awesome stories & videos in your inbox