Ayme
Ayme provides a proprietary multi-dimensional machine learning model that captures granular perceptual characteristics of food, enabling food businesses to move beyond surface-level metadata like cuisine and dietary labels. This profiling infrastructure supports precise filtering, sensory-based comparison, and data analytics for uncovering flavor preference drivers, while the consumer app tailors recipe suggestions to individual tastes and pantry contents.
- Food Technology
- Artificial Intelligence
- Data & Analytics
- Software Only
- Applications
- Consumer Goods
Funding
Founders
Founder details are not available yet.
Product
Problem
Food businesses rely on broad labels such as cuisine, category, dietary requirements, and nutritional facts, which do not capture how a dish actually feels or tastes to a person. This surface-level metadata makes it difficult to personalize discovery, predict product performance, refine offerings, or understand why certain items underperform, leading to missed opportunities across recommendation, innovation, localization, and waste reduction.
Solution
Ayme solves this with a proprietary multi-dimensional food profiling model that captures granular perceptual characteristics of food. The model tags large recipe and product datasets with a richer description of what food is actually like, not just what it is called. This profiling becomes business infrastructure, enabling more precise filtering and search, sensory-based comparison, and deeper analysis of recipes and products beyond standard functional fields. On the consumer side, the ayme app uses this profiling to tailor recipe suggestions to individual preferences and pantry contents, solving the everyday “What shall I eat?” problem.
Target Audience
Primary customers are food businesses—including retailers, meal-kit providers, and food manufacturers—seeking deeper insight into consumer flavor preferences to drive sales, plus consumers using the ayme app for personalized recipe recommendations.
Features
- Proprietary multi-dimensional machine learning model that captures granular perceptual characteristics of food
- Tags large recipe and product datasets with rich sensory descriptions beyond conventional metadata
- Enables precise filtering, search, and sensory-based comparison of food items
- Data analytics capabilities for uncovering food preference drivers and predicting product performance
- Supports strategic use cases including regional flavor localization and waste-reduction analysis
- Consumer-facing recipe app that personalizes suggestions based on user taste preferences and available pantry ingredients