Pricing    |      Food & Beverages   |     Multi-regional

The Client: A multi-regional manufacturer known for its diverse food and beverage portfolios.

The Challenge: The Revenue Growth Management (RGM) team needed to optimize the pricing of their premium beverage line which is also the largest product line in the portfolio without sell-out visibility.

The Approach: To model different price change scenarios, the manufacturer provided sell-in data, segmented by hospitality (hotels, restaurants, cafes, bars) and non hospitality buyers, to the Buynomics team to train its proprietary Virtual Shoppers AI.

Before adopting Buynomics’, the manufacturer lacked a reliable way to evaluate the impact of the price increases across the portfolio due to the absence of POS data. 

Buynomics’ Virtual Shoppers AI, an agent-based simulation model, was trained on the manufacturer’s sell-in data, since sell-out data was not available.

By running a range of pricing and distribution scenarios in Buynomics’ platform, the RGM team identified the most relevant options and assessed the impact of price changes at both the product-line and total-portfolio levels. 

Model preparation 

• Data calibration: To ensure the most accurate elasticity predictions, Buynomics first applied a deseasonalization and detrending process to the sell-in data.

• Scenario simulation: Once the data was calibrated and Buynomics AI model was trained, the RGM team started testing different scenarios in the Buynomics platform.

Portfolio pricing optimization

• Portfolio optimization: After rigorously testing multiple pricing scenarios, the team implemented a differentiated set of price increases across the portfolio, resulting in an average overall increase of 7%.

Shopper response

• Value perception shift: This configuration resulted in a shift in the value perception of the portfolio products, which was reflected in a minimal loss of sales across the portfolio.
  Note: their star product even gained sales based on portfolio cross effects.