Bayesian algorithmic perfumery: A Hierarchical Relevance Vector Machine for the Estimation of Personalized Fragrance Preferences based on Three Sensory Layers and Jungian Personality Archetypes

TL;DR

This paper introduces a hierarchical Bayesian model that personalizes fragrance recommendations by linking scent preferences to Jungian personality archetypes, enabling adaptive and interpretable suggestions.

Contribution

It presents a novel hierarchical Bayesian framework combining psychological archetypes with machine learning for personalized fragrance preference prediction.

Findings

Effective integration of Jungian archetypes with Bayesian modeling

Improved personalization through iterative Bayesian updating

Potential for enhanced sensory-based product customization

Abstract

This study explores a Bayesian algorithmic approach to personalized fragrance recommendation by integrating hierarchical Relevance Vector Machines (RVM) and Jungian personality archetypes. The paper proposes a structured model that links individual scent preferences for top, middle, and base notes to personality traits derived from Jungian archetypes, such as the Hero, Caregiver, and Explorer, among others. The algorithm utilizes Bayesian updating to dynamically refine predictions as users interact with each fragrance note. This iterative process allows for the personalization of fragrance experiences based on prior data and personality assessments, leading to adaptive and interpretable recommendations. By combining psychological theory with Bayesian machine learning, this approach addresses the complexity of modeling individual preferences while capturing user-specific and population-level trends. The study highlights the potential of hierarchical Bayesian frameworks in creating customized olfactory experiences, informed by psychological and demographic factors, contributing to advancements in personalized product design and machine learning applications in sensory-based industries.