A Machine Learning Based Funding Project Evaluation Decision Prediction

Traditional linear statistical methods cannot provide effective prediction results due to the complexity of human mind. In this paper, we apply machine learning field funding allocation decision making, and try explore whether personal characteristics evaluators help predict outcome evaluation decision? how improve accuracy rate on imbalanced dataset grant funding? Since data is characterized by distribution, propose a slacked weighted entropy tree (SWE-DT). We assign weight each class with factor. The experimental show that SWE performs well sensitivity 0.87, specificity 0.85 average 0.75. It also provides satisfied classification Area Under Curve (AUC) = 0.87. This implies proposed method accurately classified minority instances suitable datasets. By adding evaluator factors into model, improved over 9%, nearly 8% increased 7%. proves feasibility using evaluators’ as predictors. And innovatively decisions based evaluators, it enriches literature in making field.