Products mapped through a Single Source of Truth (SSOT)
$540M
Of sales opportunity for top 25 customers
1000
Opportunities identified across 4 business units through 8 patterns
Share
Background
The client is a leading global chemical producer. They are headquartered in New York City with creative, sales, and manufacturing facilities in 44 different countries. They supply the food and beverage, fragrance, home and personal care, and health and wellness end markets with innovative solutions that allow them to create the products consumers know and love.
The business goal was to drive additional revenue from their top 25 customers. After analyzing their processes, our practitioners discovered that account/client managers had a relationship driven sales process, and were not equipped with knowledge across business units and lacked understanding of products. They also had multiple constraints such as restrictions to sell specific products in specific geographies. Besides some products were customized to specific customers and could not be sold to others.
Altimetrik created a Single Source of Truth (SSOT) and enabled insights for cross sell and upsell using machine learning algorithms considering product attributes, market data, sales, constraints of geographies as well as customer spend capacity. These actionable insights were validated and made easy to consume through a user-friendly dashboard.
Pain Point
Their primary challenge was limited knowledge among account managers and client partners about their 1 million+ products spread across ~20 planning units, while the product hierarchy was expanding rapidly due to acquisitions and innovations. It became difficult to keep track of new releases and accordingly pitch them to the client. The traditional system was more of a relationship driven pull strategy (receive requirements from client and map to existing product or custom-made product), than a push strategy (creating products or pushing existing products to new and existing clients). Additionally, there were rules and regulations with regards to specific ingredients not legally permissible to be sold in multiple countries.
By creating a system which enables insights into the massive and complex product system mapped to their markets, account managers and client partners could be equipped to pitch the right product to the right customer in an efficient way.
Key Objective
An ensemble of machine learning algorithms to identify patterns in sales, and process based on attributes identified to generate cross sell and upsell recommendations.
Integrate with existing architecture.
Generate visual report
Solution
Create Single Source of Truth
Identified key variables across data sets that could be used to generate recommendations.
Created pipelines for key interfaces – invoice, product master, customer master, market intelligence, customer spend capacity.
Built ensemble of algorithms to generate recommendations
Identified patterns in the sales to generate rules.
Built in business constraints of different verticals and geographies.
Customer spend capability taken into consideration.
Generated recommendations across top 5 focus business units and geographies.
Relevancy Check Performance
Use of multiple attributes from historical sales data to check relevancy of recommendations.
Validation of recommendations through secondary research.
Continuous model development through iterations
Cadence with account managers to understand patterns and implementation degree of the recommendations.
Modifications to the rules of the algorithms.
Outcomes
$540M
of sales opportunity for top 25 customers.
1000
opportunities identified across 4 business units through & patterns.
