SME-ODA: A MACHINE LEARNING DRIVEN PLATFORM FOR DATA INTEGRATION AND ANALYSIS IN SMALL AND MEDIUM ENTERPRISES (SMEs)

As digital businesses grow massively, small and medium businesses (SMEs) must make decisions using their pre-compiled or online data. However, many SMEs struggle because their data are stored on the different online platforms where they used to transact their businesses, making it hard to make good business choices. The primary objective of this study is to determine how well the five (5) selected machine learning models like K-Means Clustering, Random Forest, XG Boost, Support Vector Machine (SVM)m and Logistic Regression, worked to support small and medium-sized businesses (SMEs) in improving customers by maximizing decision making. The findings demonstrated that the developed application with machine learning driven approach for SMEs successfully integrated and processed data, which improved efficiency and actionable insights. The results revealed that ML models outperform traditional statistical methods in predicting customer behavior and enable SMEs to make informed decisions based on real-time data analysis. It also highlights how machine learning has transformed SME operations and how companies may use analytics to gain a competitive advantage despite resource constraints. Future application of ML models should focus on implementing advanced machine learning algorithms for customer behavior prediction, enhancing the platform's predictive models with real-time data processing capabilities, and establishing comprehensive data privacy frameworks aligned with the country's data protection regulations.