This paper investigates the factors influencing susceptibility to phishing attacks using a machine learning approach with explainable artificial intelligence (XAI). The study aims to provide practical insights and personalized recommendations to individuals to mitigate their risk of falling victim to phishing. The research employs a deep neural network (DNN) model, specifically a multi-layer perceptron (MLP), and utilizes SHAP (SHapley Additive exPlanations) for interpretability. The dataset consists of 504 participants who completed a pre-campaign survey, with 121 individuals clicking on simulated phishing emails. The DNN model achieved an accuracy of 78%, recall of 71%, and precision of 57%. The analysis reveals that psychological factors such as impulsivity and conscientiousness, along with appropriate online security habits, significantly affect susceptibility to phishing. The SHAP method provides local explanations for individual predictions, allowing for personalized recommendations based on specific circumstances. The study contributes to the literature by offering personalized guidance and enhancing the understanding of factors influencing phishing susceptibility.This paper investigates the factors influencing susceptibility to phishing attacks using a machine learning approach with explainable artificial intelligence (XAI). The study aims to provide practical insights and personalized recommendations to individuals to mitigate their risk of falling victim to phishing. The research employs a deep neural network (DNN) model, specifically a multi-layer perceptron (MLP), and utilizes SHAP (SHapley Additive exPlanations) for interpretability. The dataset consists of 504 participants who completed a pre-campaign survey, with 121 individuals clicking on simulated phishing emails. The DNN model achieved an accuracy of 78%, recall of 71%, and precision of 57%. The analysis reveals that psychological factors such as impulsivity and conscientiousness, along with appropriate online security habits, significantly affect susceptibility to phishing. The SHAP method provides local explanations for individual predictions, allowing for personalized recommendations based on specific circumstances. The study contributes to the literature by offering personalized guidance and enhancing the understanding of factors influencing phishing susceptibility.