VENDORVISTA-VENDOR PERFORMANCE ANALYSIS AND RISK FORECASTING SYSTEM

In order to automate and improve conventional vendor evaluation procedures this paper introduced VendorVista a machine learning-based vendor performance analysis and risk forecasting system. The system successfully overcomes the shortcomings of manual evaluation techniques including subjectivity inconsistent results and a lack of predictive power.   VendorVista utilizes historical vendor data, trend analysis, and machine learning techniques to predict future performance scores and classify vendors into different risk levels. By incorporating multiple evaluation parameters such as delivery performance, quality metrics, and service ratings, the system ensures a comprehensive and reliable assessment of vendor performance.   The implementation of a Flask-based backend and an interactive web interface enables seamless integration, real-time predictions, and clear visualization of results through charts and dashboards. The system demonstrates consistent performance, accurate predictions, and improved usability during testing.   Overall, VendorVista highlights the practical application of machine learning in supply chain and vendor management domains. It supports data-driven decision-making, reduces manual effort, and improves efficiency. In the future, the system can be further enhanced by integrating real-time data sources, advanced predictive models, and additional analytics features to make it more robust and scalable for enterprise-level applications.

1.       an Goodfellow, Yoshua Bengio, and Aaron Courville, Deep Learning, MIT Press (2016). 2.   Tom M. Mitchell, Machine Learning, McGraw-Hill Education, 1997. 3.   Aurelien Geron, Hands-On Machine Learning with Scikit-Learn and TensorFlow, O’Reilly Media, 2017. 4.      Scikit-learn Documentation, “Machine Learning in Python,” [Online]. 5.         Pandas Documentation, “Data Analysis and Manipulation Tool,”    Availableat: https://pandas.pydata.org/ 6.  NumPy Documentation, “Numerical Computing with Python,” Available: https://numpy.org/ 7.                   Flask Documentation,“The  Flask https://flask.palletsprojects.com/ 8.       Chart. js Documentation, “Simple, clean and engaging HTML5 based JavaScript charts,” Available: https://www.chartjs.org/ 9.        W.J. Conover, Practical Nonparametric Statistics, Wiley and Sons, 1999. 10.             Supply Chain Risk Management Literature, Aqrious Research Paper and Articles related with Vendors Performance Evaluation.