Flipkart bets big on Artificial Intelligence to understand consumer behaviour

From ‘Virat Kohli’ jeans to sports shoes, e-tailer uses technology to predict buyers’ choice

October 21, 2017 06:50 pm | Updated 06:51 pm IST - BENGALURU

NEW DELHI, 06/10/2014: Flipkart today launched its biggest sale with discounts in 70 categories. The online marketplace is calling it 'The Big Billion Day' and says it has dedicated 10,000 field staff to fulfill orders, in New Delhi on October 06, 2014.  
Photo: V. Sudershan

NEW DELHI, 06/10/2014: Flipkart today launched its biggest sale with discounts in 70 categories. The online marketplace is calling it 'The Big Billion Day' and says it has dedicated 10,000 field staff to fulfill orders, in New Delhi on October 06, 2014. Photo: V. Sudershan

Standing tall alongside multinational companies like Cisco in East Bengaluru’s tech suburb is one of the office buildings of home-grown online retailer Flipkart. As one enters the facility, a huge flat-panel display in the lobby gives real-time insights about the products Indians are buying and what is trending in the country — from black saris to ‘Virat Kohli’ jeans. This information comes with the help of a data scientist team and an in-house built technology platform that uses analytics to mine hidden insights, patterns and unknown correlations from large chunks of data.

“You can sit there, grab a lunch and in 20 minutes, you would understand what is trending in India,” said Ram Papatla, vice-president, product management at Flipkart, in an interview. “It is representative of all our customers.”

Flipkart is betting big on technologies such as data analytics and artificial intelligence (AI), and machine learning to understand and predict consumer behaviour.

AI aims to build machines that can simulate human intelligence processes, while Stanford University describes machine learning (ML) as “the science of getting computers to act without being explicitly programmed.”

For instance, Flipkart, which has a registered customer base of more than 100 million, analyses consumers when they visit its homepage across channels like mobile app and web, and desktop. “We have machine learning based techniques to (predict) the content the customer is most likely going to click on,” said Vikram Sharma, director of product at Flipkart. Based on the past history, these techniques also help the firm identify other elements such as age and gender.

Such technologies are expected to give Flipkart an edge in the battle against Amazon, the world’s largest online retailer, which is rapidly gaining share in India’s online retail market. The country’s e-commerce sales are expected to grow at a 30% compound annual growth rate through FY 2027 and touch $200 billion of gross merchandise value, according to global financial services firm Morgan Stanley.

Flipkart, which had in excess of $4 billion of cash on the balance sheet after an undisclosed financing round from SoftBank’s $93 billion Vision Fund in August, is now penetrating deeper into the Indian market.

The AI and ML-based techniques are helping the firm to understand what the consumers actually meant when they searched for products and then throw up the relevant results quickly. For example, users from metros may be aware that Wrogn is ace cricketer Virat Kohli’s fashion brand. But Flipkart said consumers from tier-2 and tier-3 regions would search for the brand’s denim trousers as ‘Virat Kohli jeans’ and the demand would be far higher than in the cities.

“We have to understand that ‘Virat Kohli jeans’ means Wrogn (jeans),” said Suraj Marpak, director of product-search, at Flipkart. In another instance, he said the firm gets a lot of queries from Uttar Pradesh for Action Shoes. “For rest of India it is a brand, but in U.P. it means sports shoes,” said Mr. Marpak, an alumnus of IIT-Madras.

Flipkart had also unveiled Mira, an AI-based conversational search experience, which allows the firm to talk to users as they look for products. It guides the consumers with shopping ideas, offers and recommendations relevant to them.

Data protection

When asked how the company makes sure that the data privacy of consumers is protected, Mr. Papatla said the company takes a lot of rigours to protect the personal and financial information. He said the firm looks at the data from an aggregate perspective and obfuscates the stored data. “We treat our customer data with white gloves,” he said.

0 / 0
Sign in to unlock member-only benefits!
  • Access 10 free stories every month
  • Save stories to read later
  • Access to comment on every story
  • Sign-up/manage your newsletter subscriptions with a single click
  • Get notified by email for early access to discounts & offers on our products
Sign in

Comments

Comments have to be in English, and in full sentences. They cannot be abusive or personal. Please abide by our community guidelines for posting your comments.

We have migrated to a new commenting platform. If you are already a registered user of The Hindu and logged in, you may continue to engage with our articles. If you do not have an account please register and login to post comments. Users can access their older comments by logging into their accounts on Vuukle.