The Effect of Handling Imbalanced Datasets Methods on Prediction of Entrepreneurial Competency in University Students

As of today, entrepreneurs and entrepreneurship are considered to be the integral parts economic technological advancements. Entrepreneurs promoted in many countries because their high return on investment opportunities both terms income new inventions. Numerous studies prove that have traits common these can correlate with each other. Based traits, potential predicted, current improved by realising weak sides ones who wish provided insights. A machine learning approach light way for a better rewarding future entrepreneurship, helping goals significantly. There exist several prediction entrepreneurial competency use algorithms. Most methods perform accuracy F1-score imbalanced data instead data. This study focuses utilizing class handling increase performance. Random Oversampling, Undersampling, SMOTE, NearMiss used this purpose study. The performance algorithms Imbalanced Data Handling is compared without methods. comparison shows better.