The perfume industry is undergoing significant growth, driving the need to understand consumer preferences, particularly in men’s fragrances, to optimize business strategies. This study aims to analyze and uncover men’s fragrance preferences, using machine learning techniques. A dataset of approximately 1,000 men's perfume records from Kaggle was utilized, where systematic methodologies were employed. Data preprocessing involved handling missing values, removing duplicates, standardizing categorical entries, and performing feature engineering by extracting geographic information from item locations. Exploratory Data Analysis (EDA) was conducted to uncover data distribution. Clustering analysis using DBSCAN revealed consumer segments. Additionally, regression analysis was used to predict sales based on price and location, employing a linear regression model evaluated with metrics like Mean Squared Error (MSE). The findings indicate that price exhibits a complex relationship with sales; while affordable products drive higher sales volumes, premium-priced items cater to a niche yet impactful market segment. Geographic location plays a pivotal role in sales patterns. Clustering analysis reveals two distinct consumer segments: one driven by price sensitivity and another oriented towards premium preferences, influenced by regional factors. Regression analysis demonstrated a negative correlation between price and sales volume, with a coefficient of -1.81, while availability positively influenced sales with a coefficient of 8.36. Despite a moderate model fit (R² = 0.17), the analysis highlights key market dynamics. These insights emphasize the importance of leveraging data-driven strategies to develop targeted marketing campaigns, optimize inventory management and refine market segmentation.