Experimental Development of Learning based Consumer Behavior Recognition System using Artificial Intelligence Principle

In this research, the Bagging-KNN (K-Nearest Neighbors) cla ssifier was used to build a customer behavior identification system and test its efficacy. The study's goal is to develop a reliable method for identifying and categorizing various customer behaviors, which will provide useful information to companies and marketers. To achieve this, a dataset of consumer behavior patterns was preprocessed and transformed, and the Bagging-KNN ensemble technique was applied to enhance model performance. The study encompasses detailed experimental procedures, including feature engineering, model training, and validation using cross-validation methods. Results are presented in terms of accuracy, precision, recall, and F1-score, highlighting the system's capability to effectively classify consumer behaviors. The findings demonstrate the efficacy of the Bagging-KNN classifier for consumer behavior recognition, providing a valuable foundation for enhancing marketing strategies and customer engagement in various industries. The Proposed Model emerges as the leading performer after feature extraction, demonstrating outstanding accuracy at 0.98. This indicates its ability to accurately classify 98% of instances, underscoring its remarkable proficiency in this specific task.