How Amazon, Flipkart use data analytics to predict what you are going to buy2 min read . Updated: 16 Nov 2018, 01:49 PM IST
Data analytics helps e-commerce players like Amazon and Flipkart to identify both loyal and new customers by using data extraction and segmentation for tracking browsing habits and spending patterns.
New Delhi: Have you ever noticed that online advertisements of a product spring up after you have searched for it on an e-commerce website? Such targeted advertising, meant to remind you of unfinished business, is a result of high-end data analytics, machine learning and complex algorithms to bolster sales. Amazon, Flipkart and other e-commerce players keep track of every click you make on their portals and then predict what you are most likely to buy from them.
EY India’s analytics expert N. Balaji, who advises several leading e-commerce players, says the identification of the target customer group to whom the online ads will be displayed on blogs, news websites and content streaming websites involves advanced machine learning.
“This hyper-personalization of ads harnesses consumer data to deliver ads to the right person at the right time. It is meant to anticipate individual needs and improve the overall customer experience," he told Livemint.
Data analytics helps to identify both loyal and new customers by using data extraction and segmentation for tracking browsing habits and spending patterns. The technology allows e-commerce companies to customize their offerings and promotions.
Walmart-backed Flipkart, India’s largest e-commerce player that also owns Myntra and Jabong, analyses every click and touch in every user session to construct something called the ‘journey’ of each customer.
“The journey of users helps us understand their flow through the Flipkart app and predict their next purchase," a Flipkart spokesperson said.
For example, when a customer researches through the catalogues of a product range, the search patterns are recorded and a persona is created for the customer so that when he returns to the website, the searching time is drastically reduced by showing the most relevant product that the customer could be interested in buying.
When you are buying a mobile phone, out of the millions of products in the catalogue, the system correctly matches the most probable product you will purchase next -- a mobile case or a screen protector – an example of content-based filtering. Also, the system can recommend products based on the person’s persona or the persona of a similar customer from the same demography.
“While this sounds really simple, to implement this on the scale of a catalogue that has billions of products requires a phenomenal amount of software and hardware. With the advent of machine learning techniques, the recommender system has reached its next level in evolution," explains EY India’s partner N. Balaji.
Flipkart says each of its customers has one profile but it creates a unique session every time the user returns to the site. All the sessions are then connected to enrich the user profile and build the user journey on Flipkart, says a company spokesperson.