Product recommendations

Product Recommendations forecast product popularity, augmenting product information with layers of information ranging from general to specific sensory descriptions and temporal dominance of sensation. FlavorID® can also be deployed in online recommendations. Building a successful recommender is challenging and highly complex. Being accurate is not enough. Success = the balance between serendipity (discovery or novelty) and familiar. Foodpairing is able to deliver on this.

See this solution at work
View the story

Why do it?

  • Increase consumer experience on e-commerce platforms by offering flavor navigation or flavor recommendations, guiding your customers towards products they will like.
  • Increase product discovery by serendipity.
  • Get better insight into your consumer by collecting preferences and dietary requirements.

Questions

  • What products should I try?
  • How do I explain the flavor of my product at dummy or expert level?
  • What is the music fitting my product?
  • What is the color matching my product?

What do you get?

01

Product recommendations

Based on customer data

02

Serendipity

Understand chance flavor combinations and likability rankings

Value proposition / Solution USP

Increase customer experience by providing good food and drink recommendations. Increase personalization by recommending and/or ranking food products for an individual consumer. Increase basket size with smarter recommendations.

Goals

> Deliver a customer centric and engaging flavor or product recommendation tool.
> Provide intuitive flavor matches based on an open ended set of simple flavor led user inputs.
> Extend a user’s flavor experience by including products that sit outside their immediate preferences but are similar enough to spark interest.
> Get better insights into the flavor preferences of your core consumer.
> Augment product information.

Key measures

> FlavorID®

Configuration

> Connect to the FlavorID® platform, which is GDPR compliant for storing customer data.

Data sources

> FlavorID
> Analytical aroma data via GC-MS
> Analytica taste data via HPLC and photometric methods

Capabilities

> Aroma analysis
> Liking prediction on all possible variations within a specific flavor camp

Innovation cycle

Launch & activation

loop

Target audience

> Marketing

Want to discover more?