PERSON-Personalized Expert Recommendation System for Optimized Nutrition.

Area of Science:

• Nutritional Science
• Bioinformatics
• Computer Science

Background:

• Personalized diets are increasingly popular, driven by nutrigenetics and genetic testing.
• Current recommendation systems struggle with data complexity and scalability for daily personalized nutrition.
• Bridging the gap between genetic information and practical dietary advice remains a challenge.

Purpose of the Study:

• To introduce a personalized expert recommendation system for optimized nutrition.
• To enable direct-to-consumer personalized grocery product filtering and recommendation.
• To address the limitations of current systems in connecting genetic data to dietary choices.

Main Methods:

• A deep learning neural network model for automatic product categorization.
• Word embedding for generalized data representation to ensure scalability with new data.
• A filtering model integrating individual genetic data with phenotypic information.

Main Results:

• The system successfully categorizes grocery products using deep learning.
• Scalability is achieved through generalized word embedding representations.
• Product filtering based on genetic and phenotypic data was validated via a case study.

Conclusions:

• The developed system effectively filters and recommends personalized grocery products.
• It addresses key barriers in personalized nutrition, namely data complexity and system scalability.
• This represents a significant step towards practical, consumer-facing nutrigenetic applications.