Leading Frozen Foods Company Uses Ivy SKU Recommender for Store-specific Recommendations

With the Frozen Food market predicted to grow to $312.3 billion by 2025, it is increasingly critical for companies to leverage data analytics and AI/ML to gain sales insights into product distribution and sales strategy effectiveness.

One of our customers, the Indian subsidiary of a leading Canadian multinational Frozen Food manufacturer, recently embarked on a digital transformation of its sales force to improve product distribution, reduce out-of-stock, and increase sales.

The first phase of this digital transformation included moving to the cloud and using a mobile app to track distribution activities. In 2018, the Frozen Food company went live with Ivy Cloud Distribution Management System (DMS) and the Sales Force Automation (SFA) mobile app.

However, the second phase of this digital transformation was a real differentiator. The company was looking for insight generation to power their field force on which actions to take while visiting a retail store. For this, we worked with the Frozen Food giant to implement our SKU Recommender solution, a Best-in-class Guided Selling Platform for Consumer Goods, on top of Ivy Cloud DMS and SFA app in 2022. Ivy Recommender generates store-specific insights and recommendations to help enhance sales and improve business outcomes.

Dealing with the Data Deluge

One of the biggest challenges of the Frozen Food company was analyzing data gathered from the Indian market for insights. India is one of their large markets in Asia due to a large customer base for its potato products. The company was already collecting market-specific data from the geography with Ivy DMS and Ivy SFA app.

The Frozen Food company needed a solution to make data digestible for the sales force while generating store-specific actionable insights. The company wanted to incorporate Artificial Intelligence and Machine Learning models to curate insights and feed them into their Sales Force Automation (SFA) app for the reps.

Some of the business challenges of the Frozen Food giant included generating more lines per call, increasing sales of new SKUs in the market, and increasing the number of products sold per retail store visit.

Next-best SKU recommendations with AI/ML

We implemented Ivy Recommender for the company in 2022, which analyzed their business data for insights and recommendations tailored to specific stores and visits.

The solution provides two kinds of recommendations- FITsell and UPSell. Under FITsell, Ivy Recommender gives product recommendations based on fast-moving promotions by analyzing past sales. Under UPsell, it goes deeper and understands peer store parameters to recommend the Next-best SKU and Predicted Order Quantity for a specific store in a visit.

For implementing Ivy Recommender for the company, we took a phased approach and made the solution active for retailer-specific recommendations in batches.

  • In the first phase, Ivy Recommender was activated for a set of 200+ retailers for the company.
  • By the end of 4 months, we activated Ivy Recommender for 25,000+ retailers in the company’s distribution network.
  • In the initial run, the accuracy of recommendations was around 30%, and it has been increasing each week.
  • The solution is used by 300+ users/sales reps catering to 25k retailers for the Frozen Food company.

Generating Results that Matter

The outcomes of implementing Ivy Recommender for the company were very encouraging, and they speak for the efficacy of the recommendations.

14% Increase in Sales

26% Increase in Sales Volume

35% Boost in Lines per Call

21% Increase in New lines

Overall, Ivy’s AI/ML-based solution- Ivy Recommender, helped one of Asia’s largest frozen food manufacturers achieve significant growth and generate more sales and revenue, showcasing the power of technological solutions in meeting business needs. We launched Ivy Recommender in 2021, and the company was one of the initial adopters of the solution from our existing customer base.

*The metrics identified are subject to vary based on parameters like data quality, data quantity, and volume of data used in training the intelligent system.

Share this

Recent Posts

test

tsdfsfsf

en_USEnglish (United States)