Published Paper Details:

Customer segmentation and behavior prediction play pivotal roles in enhancing business strategies, personalizing marketing campaigns, and optimizing inventory management in E-commerce platforms. This research focuses on analyzing a comprehensive E-commerce dataset containing transactions of ~4,000 customers over one year to uncover purchasing patterns, classify customer types, and anticipate future buying behaviors. Data preprocessing involved handling missing values, removing duplicates, and identifying order cancellations to ensure clean and reliable data for analysis.A detailed exploratory data analysis (EDA) was conducted to investigate product categories, customer attributes, and purchase trends. Advanced clustering techniques, including k-Means, were employed to segment customers into meaningful groups based on purchase frequency, spending patterns, and preferences. Machine learning models, such as Support Vector Machines (SVM), Logistic Regression, Decision Trees, Random Forest, Gradient Boosting, and k-Nearest Neighbors (k-NN), were utilized to classify customers into predefined categories, achieving moderate to high precision scores.To enhance predictive accuracy, deep learning models were incorporated. A Convolutional Neural Network (CNN) achieved the highest precision of 94.94%, leveraging its capability to extract complex patterns and relationships from high-dimensional data. An Artificial Neural Network (ANN) also demonstrated strong performance with a precision of 91.62%. Comparative analyses revealed the superiority of CNN and ANN over traditional machine learning models in handling complex datasets.This study introduces a novel approach to predicting customer behavior based on their first transaction. By integrating insights from clustering, classification models, and deep learning techniques, this research provides a robust framework for understanding customer dynamics and forecasting future purchases. The proposed methods empower businesses to optimize decision-making, improve customer satisfaction, and achieve sustainable growth in competitive E-commerce environments.