Snap2Insight
Gautam Malu began their work experience in 2015 as a Google Summer of Code student for CentOS. In 2014, they worked as a Software Developer at S-Labs, where they developed a proof of concept for simultaneous multi-booting of Ubuntu on Samsung Arndale Exynos boards using Xen 4.5 Hypervisor. In 2015, Gautam also worked as a Consultant at Deep Learn Labs. In 2017, they participated as a Google Summer of Code student at Opendetection, where they added CNN based classifiers and detectors to the OpenDetection framework. Gautam'smost recent role is as a Computer Vision Lead at Snap2Insight since 2018. At Snap2Insight, Gautam uses image recognition techniques to provide visibility into product merchandising on shelves and the execution of trade promotions. Gautam'swork aims to disrupt how retail shelf and promotion execution is measured and analyzed, ultimately helping brands improve execution and increase sales.
Gautam Malu completed their Bachelor's Degree in Electrical, Electronics and Communications Engineering from the International Institute of Information Technology Hyderabad (IIITH) from 2007 to 2011. Following that, they pursued a Master's Degree in Cognitive Science from the same institution from 2012 to 2017.
This person is not in any offices
Snap2Insight
One of the leading health and personal care brands had planned a promotional campaign offering bonus packs at a promotional price in the face of some intense competition from its rival brand. Their customer (Team Leader for the brand at a retail chain) had worked with a major retailer to put up pallet displays with eye catching graphic skirtsacross all its stores nationwide. Their customer has often seen poor sales lift across 30-40% stores for such campaigns in the past. Snap2Insight was tasked to verify quality of execution nationwide and identify stores with incomplete execution or no execution. Leveraging their partnership with a leading crowdsourcing vendor, they quickly gathered photos of displays from every single store and using their patent pending Deep Learning technology, they analysed them to recognise SKUs stocked, present of graphic skirt, promotional price and type of display put up. Using execution scores they provided for each store covered under this promotional campaign, their customer worked with their retail coverage partner (merchandiser) to prioritise and fix all stores with low execution score and high potential for sales lift, thereby improving sales and achieving break over for over 90% of stores.