BOXX.AI: Leveraging AI to Deliver Magical Online Shopping Experience

CIO Vendor Shopping is inherently an intimate task – you spend their hard-earned money to buy your dreams. The shopkeepers of yesteryears understood this – they would try to understand your needs, your passions, your context and then present the most suitable products for you, while incorporating your active and passive feedback every time.

However, with the advent of e-commerce, the scale of shopping changed, both in terms of number of customers and products. And with it, the experience became more transactional, removing the magic out of shopping.

Ajay Kashyap, Prakhar Raj and Shitiz Bansal are batch mates from IIT. They co-founded Boxx. ai to work with e-commerce companies for recreating this magic with the help of Artificial Intelligence. Speaking of their AI-driven product, Kashyap explains, “Our algorithms and powerful compute engines are designed to know your customers, remember their past interactions, understand their context, predict the most relevant and personalized products, and then further keep learning and refining the same in real-time by gauging their reactions; and all of this is done for millions of customers, across tens of thousands of products within 200 milliseconds.”

From a business perspective, such personalized experiences result in customers visiting the e-commerce site more often, spending more time and buying more often.

40% Increase in the Topline Powered by Powerful Algorithms is the world’s only plug-and-play omnichannel personalization engine. It leverages the power of AI to enable the e-commerce players touch their end customers with a magical shopping experience, while driving a business benefit of 40 percent increase in topline.

Based in Bangalore, clientele includes leading names in e-commerce industry such as Nearbuy, TataCliq, Jabong, Clovia, Voylla, ABOF, Spencers, FabIndia, Caratlaneand Zivame.

Divulging’s methodology, Kashyap explains, “’s ever-learning algorithms find hidden patterns in the data and identify the most relevant and personalized products for each customer based on their probability to click or buy. The algorithms are constantly learning and genetically evolving to continually improve the predictions in real-time with any new piece of data made available to it, like a new click, purchase, search or filter. The algorithms use neural network to enable real-time learning and ease to keep adding new feature-sets to cater to different use-cases.”’s algorithms start with industry-standard collaborative-filtering and content-based recommendation algorithms, used with product embedding to make it scalable to large amounts of data.
Next, the context layer is added to cater to the nuances in choices based on seasons, date of month, day of week, festivals, events, location and weather. For example, the machine would understand that the choice of apparel for a Delhi girl would be very different from a Chennai girl, and would also keep evolving with seasons, weather and the latest fashion trends. is the world’s only plug-and-play omnichannel personalization engine

Further, the temporal layer is added to cater to recency of interactions, order of buying products, and periodicity of purchases in shopping. For example, the machine would learn that Mrs. Chaddha buys 10 kg atta every month, which means that she probably has a family of 5, and would require 1 kg salt every 45 days.

Omni Channel Reach
Kashyap continues, “Further, armed with the knowledge of most personalized and relevant products for each user, the product is then able to communicate the same across every touch-point - on the website or app, with digital marketing and advertisements”.

For instance, on the website of an e-commerce portal, on any page, EACH user is shown only the most personalized and relevant products, reordered specifically for her in the order of her probability to buy, thus, typically increasing the conversions by 40%.

Similarly, when an e-commerce company send an emails or notifications, with’s AI capabilities, they are able to personalize each and every communication to contain only the products that the corresponding user is most likely to buy, thus increasing the click rates by 40%.

Further, e-commerce companies are able to personalize each advertisement (on Facebook, Instagram or Google ad network) to each customer with the most personalized products, thus increasing the ROI from advertisements by 40%.

Ease of Integration and Use
Another strength that differentiates is their immense focus on providing a smooth experience in integrating the product with the business. Kashyap elaborates “We have been able to develop the product with multiple integrations options, including API’s, SDK’s in all languages, Magento Plugin and Google Tag Manager connector. This helps the clients integrate the product and start seeing the results within a week.”’s feature-rich application allows complete cross-channel campaign management capability from the interface itself. Further, the application’s tracking and reporting abilities complete the product offerings with the provisions to view and track real-time conversion funnel and drill downs.