Improving Inventory Management and accelerating time to insight
About the Organization:
Swiggy is India’s leading on-demand delivery platform with a tech-first approach to logistics and a solution-first approach to consumer demands. With a presence in 500 cities across India, they deliver unparalleled convenience driven by continuous innovation.
From starting out as a hyperlocal food delivery service in 2014, to becoming a logistics hub of excellence today, their capabilities result not only in lightning-fast delivery for customers, but also in a productive and fulfilling experience for our employees.
Challenge: Replacing an Inefficient, Cumbersome, Manual Process
Swiggy analysis was completed on a monthly basis via an inefficient, cumbersome and manual process that originated with CSV extracts which leads to understock or overstock. Overstocking can lead to decisions like marking down the item’s price, which increases sales turnover and having limited stock results in lost sales and dissatisfied customers who then purchase from the competition.
A scalable, flexible, transparent, and easy-to-update solution was needed, which also signiﬁcantly accelerated the time to insight. They would like to predict at-least 3 months of sales for 50 Items at 10 Different Stores.
Solution: An End-to-End Data pipeline and automated Data Science Solution for Inventory Forecasting
To aid in solving the above problems, we built the Forecasting Platform, a web application built using KNIME that allows decision makers and stakeholders to be as equally involved as data engineers and data scientists in creating a pipeline.
The solution provides several advantages over historical forecasting solutions:
Knoldus helps Swiggy to develop a Guided Analytics application. With the help of this application, Swiggy creates data visualization, interactive and scheduled dashboards and inventory forecasting models as well as generate forecasting for their business intelligently and collaboratively by:
Once the reports and visualizations are generated, data scientists, business users, and domain experts can collaborate on the final results.