How Amazon's scientists in India built tech to protect against coronavirus

The e-commerce giant Amazon's machine learning team in India is also developing innovations for customers worldwide

As soon as the coronavirus pandemic struck, Rajeev Rastogi, vice-president of machine learning at e-commerce giant Amazon India, became interested in what he and his team could do as scientists to keep people safe and help them get what they need during these trying times. 

“Could we use technology to generate an infection risk score for each individual? These scores could be leveraged by governments and organisations to prioritise testing and identify individuals to quarantine,” says Rastogi in a company blog post.

Covid-19 spreads through contacts. Many governments have developed contact-tracing apps that use Bluetooth signals on mobile phones to track social contacts among individuals. However, it is challenging to use this fine-grained contact data of individuals to estimate an infection risk score for each individual. This is because the probability of infection transmission through a contact depends on the duration, distance, and location (indoors, outdoors) of the contact. Furthermore, individuals may have indirectly come in contact with a person who has tested positive for Covid-19. Or they may have come in contact with an infected person, but during the period when he or she was not contagious.

“I worked with fellow scientists to develop a probabilistic graphical model called CRISP for Covid-19 infection spread through contacts between individuals,” says Rastogi.

The model builds off the SEIR (susceptible-exposed-infectious-removed) approach that is commonly used to track the different epidemiological status of individuals. The model captures the transitions between these different states, while also accounting for test outcomes. The team developed an algorithm to draw samples of the latent infection status of each individual, given data about contacts and test results. These infection status samples are then used to compute infection risk scores for each individual. The team also developed an algorithm to infer the infection transmission probability for each contact taking into account factors such as contact duration, distance, and location. 

“Also during the pandemic, our operations team built virtual pickup points to deliver packages to customers who live in quarantined apartment buildings,” says Rastogi.

The problem was about identifying customers who live in these buildings and educating them about the virtual pickup points. The team used address segmentation machine learning models to extract apartment building names from delivery addresses input by customers. It then sent emails to these customers notifying them about the new features. “Customers were really excited about this new feature — the email open rates announcing virtual pickup points were higher than 50 per cent,” says Rastogi, in the blog post.

Rastogi began his career at Bell Labs. He also served as the vice president of Yahoo Labs, where his team developed data-extraction algorithms to pull structured information from billions of webpages, and then present them to users in easily digestible ways.

He joined Amazon in 2012. His first Amazon project involved the development of algorithms to classify products into Amazon’s large and complex taxonomical structure. For example, to classify a Samsonite luggage set in ‘carry-on luggage,’ ‘suitcases’ and ‘luggage sets.’ Since then, Rastogi has been involved in utilizing science to make an impact in a number of areas that have resulted in faster, more seamless and sustainable, shopping experiences.

As vice president of machine learning at Amazon India, Rastogi is now helping his team drive innovations that have a profound impact not only on shoppers in India, but also on the company’s customers around the world.  

For example, models developed by Amazon’s scientists in India have been used globally to improve the quality of Amazon’s catalog by ensuring that for all products, images match with the title.

India is a unique market in several important ways. There are more than 600 million people online in the country. Many of them are relatively new to digital shopping. Over 85 per cent of the company’s traffic comes from a diverse range of mobile devices.  To complicate matters, mobile customers in India can experience fluctuating speeds due to congested towers and tower switching.

“We’ve developed models to predict customers who are on a slow or spotty network based on criteria like device characteristics, cell tower information, and the latency of the last request,” says Rastogi, in the blog post. “For such customers, we provide an adaptive experience and serve streamlined pages with a lower number of widgets that are easier to navigate.”

With more than 22 languages and 19,500 dialects, India is also an incredibly diverse country with strong regional preferences. A customer searching for a sari in Gujarat may be interested in a “Bandhani,” which is popular in that state, while a customer in Karnataka searching for a sari may be looking for “Mysore Silk,” a popular variety in that region. To surface regionally popular and relevant products in search results, the team has added regional sales for products as a feature in search.

A key problem in India and other emerging countries is that addresses are highly unstructured. They are also incomplete, with critical address fields such as street names missing from the address. For example, the firm has seen addresses on Amazon.in such as “Near Orion Mall, Malleswaram, Bangalore”, or “Near Bus Stand, Sambhaji Chowk, Nasik”.

Rastogi’s team has developed a machine-learning-based “address deliverability score” to identify poor quality and incomplete addresses that are difficult to locate and deliver to, and intercept them at address creation time to improve address quality. 

Amazon has also committed to reaching net-zero carbon by 2040, one decade ahead of the Paris Agreement. Science will play an extremely important role in enabling innovations that will make this happen.

At this year’s European Conference on Machine Learning, members of Rastogi’s team presented a new model for determining the best way to package a given product. Incorrect packaging is not only wasteful and bad for the environment, but it also increases packaging and concessions costs. A recently developed statistical model has helped Amazon reduce product-shipment damage in India. The team applied the model to hundreds of thousands of Amazon packages, reducing shipment damage very significantly while actually saving on shipping costs.

“This innovation is a testament to the incredible scientific talent at Amazon India,” says Rastogi. “It also speaks volumes of our desire and our ability to take on the really big problems — those that have a significant impact on the lives of our customers and the world at large.”