Machine learning based supplier defect prediction with real time risk alerts for uplift operations

ABSTRACT-Efficient supply management is regarded as an essential aspect in ensuring business success, particularly in uplift operations where the timely nature of supply and quality of products are regarded as critical factors in determining business success. The research focuses on presenting a proposal on how machine learning can be utilized in predicting defects in supply and sending timely signals. The timely nature of supply is critical in ensuring timely decisions are made in supply management. Data collected from suppliers on the quantity of ordered supplies, delay in supply, and past defects in supply were utilized in building a random forest classifier in predicting defects in supply. The suggested framework is critical in ensuring timely efficiency in uplift operations, thus ensuring any potential losses are averted by defective supply. The research has shown how machine learning can be utilized in optimizing uplift operations. Moreover, the incorporation of predictive analytics ensures timely decisions are made, thus enhancing supply chain transparency. The suggested solution is deemed to be suitable in ensuring o