Revolutionizing E-Commerce: Innovative Insights into Pricing Strategies using Regression and Classification Models

Intelligent strategies of pricing are necessary for maximization as well as satisfaction of earning and customers in e-commerce because of its dynamic nature. The study investigates the impact of different regression and classification machine learning models on optimal price setting and segmentation of user behavior. We introduced the pricing prediction models such as Linear Regression, Ridge Regression, Lasso Regression, XGBoost, and Random Forest Regressor while for user segmentation, we used Logistic Regression, Decision Trees, and Support Vector Machines (SVM). The comparison shows the advantages and disadvantages of each model and Ridge Regression performs best for regression tasks, while Support Vector Machines provide a 100 percent accuracy classification, though it can be considered for overfitting. All findings shall indulge into information regarding choosing models for data-driven pricing and segmentation in e-commerce. This is crucial considering the nature of e- commerce that is dynamic; intelligent strategies of pricing are required for maximization and satisfaction of the earning and customer. The study investigates how different regression and classification machine learning models affect optimal price settings and user behavior segmentation. We implemented the pricing strategies such as Linear Regression, Ridge Regression, Lasso Regression, XG Boost, Random Forest Regressor, and user segmentation using Logistic Regression, Decision Trees, and Support Vector Machines (SVM). The comparison made displays the strengths and weaknesses of each model where Ridge Regression performs best in regression tasks and Support Vector Machines give a 100 percent accurate classification, although-overfitting could be an issue. All findings shall involve information regarding choosing models for data- driven pricing and segmentation in e-commerce.