Our data science solution enabled MRL to maximize its margins and customer traffic through scientific pricing with simplified Ganit's pricing engine

We made a visible and measurable impact to our client's business

14%

Increase in top-line sales

9%

Increase in RGM

7%

Increase in the number of bills

5%

Increase in repeat customer rate

Challenge

Industry OVERVIEW

MRL is one of the largest retailers based out of India operating more than 800 supermarkets and 30 hypermarkets across the country. They have a portfolio of more than 3 million Store-SKU combinations belonging to a wide variety of product categories ranging from grocery food, staples, personal care, home care to apparels. The Buying & Merchandising team and the Category Managers were responsible to set the prices for the SKUs on a monthly basis.
They wanted to eliminate the heuristic-based pricing and arrive at better pricing by understanding the elasticity

THE PROBLEM

To generate prices based on a scientific pricing model with all demand driving factors considered, along with elimination of manual interventions. Gaps in the current system

Prices were set heuristically by only taking into consideration competition price benchmarks and sourcing benefits
Pricing was heuristics-based. No visibility into the elasticity of products and thereby leading to margin erosions due to inaccurate pricing
The flow of prices from Category Managers to the end store POS was a manual process prone to multiple errors and system breakdowns.

Why were we brought in?

Ganit has made a significant dent in various industries using data science and analysis. Ganit partners with clients to translate their data into a tangible, insightful plan of action that delivers on a measurable impact to the clients’ topline & bottom-line growth.

Specifically for this use case since Ganit has worked with various retailers in the past and provided them cutting edge solutions to create a measurable impact to our client’s business a major chunk of these solutions involved an AWS based architecture or services at some step making Ganit a perfectly viable choice for delivering solutions to related business problems.

Our approach

Methodology

Raw data is retrieved from Redshift, processed in an EC2 environment using Python scripts, transformed with Glue, and stored in an S3 bucket. The final output of the Python script is then stored in another S3 bucket.

After storing the results in S3, Amazon QuickSight is used for data visualization.

Our approach helps MRL to understand the elasticity of each product at store level and price the products based on their elasticity

A valuable difference

Impact

Maximized margins up to 7.9% by increasing prices of inelastic SKUs at a hyper-local and personalized manner.
Increased traffic by 11% through scientific price optimization of traffic-driving central SKUs