Explainable Machine Learning Models for Identification of Food-Related Lifestyle Factors in Chicken Meat Consumption Case in Northern Greece

A consumer’s decision-making process regarding the purchase of chicken meat is a multifaceted one, influenced by various food-related, personal, and environmental factors that interact with one another. The mediating effect food lifestyle bridges gap between consumer values environment, further shapes behavior towards consumption. This research introduces concept Food-Related Lifestyle (FRL) aims to identify explain associated consumption in Northern Greece using machine learning pipeline. To achieve this, Boruta algorithm four widely recognized classifiers were employed, achieving binary classification accuracy up 78.26%. study primarily focuses on determining items from FRL tool carry significant weight output, thereby providing valuable insights. Additionally, interpret significance these selected SHAP model. Specifically, it turns out freshness, safety, nutritional value are essential considerations for consumers their eating habits. external like health crises price fluctuations can have impact choices related findings contribute more nuanced understanding preferences, enabling industry align its offerings marketing efforts needs desires. Ultimately, this work demonstrates potential AI shaping future informs strategies effective decision-making.