Retail promotion is a dicey game that usually entails thousands (even millions) of dollars in promotional budget, and there is no hard and fast rule to understanding which promotional strategy is the most profitable.

For instance, the retail promotion of a particular product may lead to a decrease in sales of its substitutes and an increase in sales of its supplements- a classic case of cannibalization, and complementarity. It may also increase the sales of unrelated products due to higher footfall- aka the halo effect.

Manually calculating the effectiveness of each promotion would require tens of thousands of statistical models, hence posing a real challenge for retailers.

A practical option is to model using Machine Learning techniques on a Big Data architecture.

Client Introduction & Business Requirement:

Our client is a leading Cement Manufacturer in India. 

They were targeting their wholesale and retail prices at a district level, against multiple competitors. They were unsure if they were tracking against the correct benchmark, and wanted to optimize their pricing strategy to cut down losses, without losing market share.

Solution Overview:

Our Retail Promotional Optimization solution uses ML algorithms to identify features and develop models to calculate the sales and margin impact of each promotion.

This enables the retailer to stop unprofitable promotions in the future (using an in-built Simulator) or renegotiate funding for such promotions with its vendors (i.e. National Brands). 

Our solution leverages the AiLens platform which is built on a distributed processing architecture; AiLens sifts through billions of rows of transactional data to identify tens of millions of dollars in lost margins.

Solution Highlights:

  • Pre-built components
  • Unified AI Modeling
  • Capabilities for Seamless Collaboration
  • High Scalability & Security
  • Stack Agnostic AI Runtime Support

Here’s a step-by-step play of the solution:

Collect data and create variables (for promotions, pricing, holidays and weather).

→ 

Develop ML models for each SKU to determine impact of each promotion and other variables.

Calculate impact of each promotion and identify unprofitable promotions.

In this manner, the client’s data for sales, pricing, promotion and inventory were aggregated for historical data. Competitors were evaluated to identify the target price to be benchmarked at every district. Price optimization models were built to set prices at SKU and district level.

Business Benefits:

  • The solution highlights millions of dollars of margin loss on unprofitable promotions that can be renegotiated with vendors.
  • The Simulator Tool and Dashboards drive the retailer’s promotion planning and prevent future unprofitable promotions.
  • Our client witnessed an increase in operating profits by nearly 28% with just 2% increase in price in most districts.

At Knowledge Lens, we constantly work towards improving our product technologies, so your business can do more for you. We have partnered with Microsoft to provide Indian SMBs with intelligent Analytics Solutions for Supply Chain, Sales & Marketing verticals  at a nominal pay-as-you-go fee.

Customers have the ability to customize their package as per their unique business requirements. What’s more, you can engage in a 2 hour workshop led by experts & a 50% discount on POCs for qualified opportunities. 

Scale operations & drive business transformation with us. Contact us here, so we can get talking on the right tools & resources to leverage your business data and analytics.

You could also get in touch with our solution experts:

N. America region: Contact sudheesh@knowledgelens.com

Middle East region: Contact ketan@knowledgelens.com 

APAC region: Contact ganesh@knowledgelens.com 


Sneha Mary Christall

Marketing and Brand Manager, Knowledge Lens.

Leave a Reply

Your email address will not be published. Required fields are marked *