From 'Virat Kohli' jeans to sports shoes, e-tailer uses technology to predict buyers' choice
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.
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.
Source: The Hindu