Data partnership unlocks millions in sales in 5 months

A partnership renewal between global CPG and EPOS data vendor was made possible by facilitating blindfolded analytics on daily-level category & brand sales data.

Challenge

Direct data partnerships with retailers remain a mainstay of CPG analytics -- particularly for core data and data on retailer action levers.  CPGs need access to relevant data on consumption-based drivers. Retailers are a key source of this, just as CPGs possess more data on production-based drivers. This leads to a strong mutual interest for both parties to collaborate.

However, retailer data is no longer solely comprised from traditional sources such as planograms, trade plans, and EPoS and loyalty card data, as retailers begin to gather intelligence from a diverse range of digital sources, including in-store cameras and sensors, and eCommerce sites and mobile apps.  

A new approach called blind analytics enables CPGs to extract insights from retail data without needing to view the raw data, making it possible to leverage data sources that were hitherto out of reach due to commercial sensitivities or data privacy restrictions. 

In this insights-as-a-service model, AI platforms sit between the CPG and the retailer and surface patterns from integrated datasets. In time, this technology could disintermediate third-party agencies who process and resell retailer data, a development that is likely to elevate the importance of data to the commercial relationships between CPGs and retailers.

A global confectionary company wanted to prioritize its limited sales capacity, empowering their reps with dynamic trade insights to share with retailers. 

A data partnership with retailers would help them discover brand-level consumer micro-segments. In this case, the leading CPG planned to advise a UK retailer on how to drive online sales in the snacks category. This retailer had no robust way of evaluating the best media / promotional mechanics to maximise snack category performance.

So the confectionary company used SparkBeyond to renew a partnership with an EPoS data vendor, in order to leverage store-level data and equip their trade marketing teams with actionable intelligence on shopper activation. This would transform promotions from a commodity investment to a strategic lever. 

Approach

SparkBeyond’s Blindfolded Analytics analyzed both the CPG’s and EPoS company’s confidential and unshareable data to reveal granular drivers and micro-segments without exposing analysts to raw data.

Leveraging syndicated EPoS data, Field data, Socio-demographic data, Geographic data and footfall traffic data, the platform built a model to predict snack sales as a proportion of total retail sales, based on different combinations of promotions mechanics, media types and ATL activity.

The model was highly accurate, predicting the share of sales to within 0.02 percentage points of the actuals. 

Features

No items found.
No items found.

It was easier in this project since we used this outpout

Business Insights

Apply key dataset transformations through no/low-code workflows to clean, prep, and scope your datasets as needed for analysis

Predictive Models

Apply key dataset transformations through no/low-code workflows to clean, prep, and scope your datasets as needed for analysis

Micro-Segments

Apply key dataset transformations through no/low-code workflows to clean, prep, and scope your datasets as needed for analysis

Features For
External Models

Apply key dataset transformations through no/low-code workflows to clean, prep, and scope your datasets as needed for analysis

Business Automation
Rules

Apply key dataset transformations through no/low-code workflows to clean, prep, and scope your datasets as needed for analysis

Root-Cause
Analysis

Apply key dataset transformations through no/low-code workflows to clean, prep, and scope your datasets as needed for analysis

Join our event about this topic today.

Learn all about the SparkBeyond mission and product vision.

RVSP
Arrow