Rahul Goyal
Case study

Rahul Goyal

Asst. General Manager
Rahul Goyal leads the Demand Planning & Data Analytics function for India consumer products division of one of top beauty tech companies in the world. He leads the Data Driven S&OP pillar of India Supply Chain Transformation, including governance and coordination of global initiatives. He is also responsible for the acceleration of the digital transformation of planning process through the test and deployment of Machine Learning and Advanced Analytics capabilities. He has been instrumental in defining the end-to-end planning framework with criteria and methods to drive response to volatile market needs and support acceleration of the E-Commerce model . He has more than 10 years of experience across sectors like Fashion & Apparel, Consumer Healthcare, FMCG & Beauty.

Rahul earned his PGDM degree in Supply Chain & IT from National Institute of Industrial Engineering (NITIE) & B.Tech in IT from University School of Information Technology (USIT). Rahul has won various industry awards in last 10 years. He was conferred with the Best Demand Planner of the year in 2018 by ISCM. He won the prestigious Lakshya (On the Job Achievers Contest) Award at NITIE for implementing a Demand Sensing Solution in 2016. He also won the Reverse Logistics Operational Excellence Award in 2013 at Asia Supply Chain Summit. He is also a visiting faculty at prestigious Narsee Monjee Management Institute (NMIMS). He is certified in Theory of Constraints from Goldratt School, Project Management from ProThoughts & Six Sigma from ASQ Exemplar. His areas of interests are Supply Chain, Six Sigma, Block Chain, Design Thinking & Machine Learning.
Read More Read Less
Tuesday, 03 August, 2021 / 12:00 PM - 12:30 PM IST
(02:30 AM - 03:00 AM EDT)
Case Study: Drive Forecasting Accuracy, Service Levels and Availability for Ecommerce Sales Using Machine Learning

We were challenged with the unpredictability of demand in our ecommerce sales channel (contributing to 30% of the business) where forecasts had an abysmally low accuracy of less than 30%, this made it difficult to provide best in class service levels and agility to the exponentially growing channel. Moreover, the consensus process was elaborate and process was marred with redundancy and it frustrated the management team with the end results. This case study will describe the journey that L’Oréal took in the deployment of Feature engineering and Machine Learning, to improve pre-covid forecast accuracy to 80% and post-covid accuracy of 60%, an improvement of close to 100%. This led to better stock availability and hence higher service levels for the channel.

Join us to hear from Gartner experts and thought leaders.