In our weekly column, we catch up with India’s leading online pharmacy Netmeds, founded by Pradeep Dadha, to understand the company’s sharp focus on technology and how in the already crowded pharma space, the company has differentiated itself from their competitors by providing a holistic health platform that includes online consultation, diagnostics and insurance (in the future). The company, billed as “India ki Pharmacy” founded in 2015 enjoys double-digit growth and recently secured $35 million in their last funding round from their existing investors and Cambodia’s Daun Penh Cambodia Group (DPCG).
AIM spoke to Netmeds CTO Advait Suhas Pandit, who heads the Technology, Delivery Systems and Online Services for Netmeds.com wherein he handles all software requirements for customer facing touch points across mobile, web, brick and mortar stores, procurement, logistics, pharma related statutory operations, data analytics/sciences, as well as corporate IT. In the last three years, under Pandit’s direction, the engineering team has grown to be 80-people strong and has emerged as a truly pan-India pharmacy with the most updated catalogue and prices.
The company has seen a consistent growth trajectory under his technological direction. Pandit has been responsible for introducing AI/Machine Learning to bring innovation across the platform, which has benefited from operational efficiency as well as improved customer experience. Talking about the core areas he worked on, he said, “ Some of the core areas that the engineering team works on are fraud detection preventing customers from ordering over what has been prescribed, digitization of prescriptions, optimizing delivery, keeping the very dynamically changing product catalogue up-to-date, customer profiling and recommendations, demand forecasting, procurement planning, routing orders to the most optimal warehouse among other use cases”.
Chennai-headquartered company has also built a formidable pharma module in place to ensure greater accuracy in validating a prescription. The module has been in use for the last three years and helps in quicker turnaround times.
- Their module facilitates digitization of prescriptions
- Scores prescriptions based on certain mandatory data that a prescription must hold
- Reads patterns in prescriptions and finally puts out alerts to the team of pharmacists if the algorithms pick out any suspicious prescriptions or orders
How does a pharma e-marketplace differ from an ecommerce company? Talking about the subtle differences, he shared, there are certain subtleties related to the pharma vertical which is very different from traditional e-commerce. “A good example would be that of recommending products to a customer while browsing the site. We cannot recommend pharma products to a user. Therefore, we use ML and analytics to profile customers and recommend FMCG products or products that do not require a prescription that complement the pharma products the customer buys. For example, we would recommend a diabetic drink for a customer who falls under the profile of a diabetic,” said Pandit.
The company uses Machine Learning and Fuzzy Logic to map the catalogue to supplier catalogues. Over a period of time, on an average the engineering team has been able to match 80% of the supplier’s catalogue via algorithms, which helps cut down integration time tremendously. “Our algorithms have also been able to detect new pack sizes, patterns in the way suppliers name products in their catalogue, which helps in on-going synchronisation between supplier systems and ours,” said Pandit.
The team also leverages AI to forecast demand and procurement requirements by pin code and match this up to the warehouse that services the respective pin code. Forecasts are made depending on historical sales data, the type of the product, season and marketing efforts. Based on these forecasts, demands are generated to suppliers based on-storage capacity of the warehouses, supplier ratings based on their previous fulfillment rates and time taken to fulfill demands.
At Netmeds, the mantra followed for the tech stack is to designate the “appropriate tech for given problem”. For e.g. while transaction processing systems are in .NET and Java, content-based systems are in PHP and NodeJS, shared Pandit. And since the solutions are composed as microservices, their management, monitoring, scaling and feature-rollouts are much simpler. Talking about deploying containers, he shared, “We are in the process of getting started with serverless technologies such as Lambda and Fargate (serverless containers)”.
Regarding the Big Data Engine, a data-lake tracks all data using a combination of Redshift, DynamoDB, S3 and Athena. Excel, Tableau and the team uses some proprietary systems are used for data visualization. In terms of cloud, Netmeds is completely on Amazon AWS. On the customer side to ensure quick responses, extensive parallelization, CDN and edge computing is to reduce latency and get fast responses.
Rethinking People Strategies@Netmeds
Talking about their hiring strategies and the core competencies required for the engineering team, Pandit said the company is mulling the use of hackathons to fulfil their talent requirements in the second half of the year. Apart from the regular technical skills that are required for the job profile, the three other important capabilities one must have are problem solving skills, logical thinking and communication/written skills, shared Pandit. “We strongly believe that if a person is able to explain the problem, and think through it from a logical perspective, s/he will be able to solve it technically,” he said. The epharma giant is looking to expand its senior leadership team by hiring more senior resources on board to look after new initiatives, as well as strengthen their mid-level management team.
In the highly competitive, epharma market, most of the advancements would come from players that are trying to differentiate themselves with new offerings and launching new initiatives under a single platform for customers. At Netmeds, Pandit and his team is doubling down aggressively on search algorithms to show results based on the profile of the customer. “Since most of our customers search for products (even in the non-pharma category) rather than browsing through categories, we are working on search algorithms to display results based on profile,” he said.
Up next, subscriptions and refills is another key area for 2019, given how subscriptions in e-pharma is the new concept which also requires a certain level of human interaction to give the customer the confidence. Messaging bots and IVR solutions will play a pivotal role in improving these customer interactions and reminding/nudging customers about upcoming refills and subscriptions, as well as help them complete payments with ease.