Quantitative Performance Evaluation Technology Based on Sparse Oblique Trees Algorithm in Mobile Internet

Abstract

The quantitative performance evaluation is a method for evaluating an employee based on measurable factors directly related to their job. Many professionals in the modern workforce are no longer able to easily and consistently access desktop computers due to their increasingly itinerant lifestyle. Employees must be able to access contemporary employee performance management programs via mobile internet for them to be completely inclusive. Problems with the performance evaluation include the subjective one-sidedness of the evaluation indicators and the challenging measurement of the indicators. To address this drawback, the methodology used in this research was provided in order to classify employee data more precisely. The data is gathered from 227 enterprises in South Korea. At the pre-processing stage, the adaptive robust cubature kalman filtering is used to pre-process the data. The employee discipline, employee attitude, employee effort are successfully classified using sparse oblique trees algorithm (SOTA).To increase the SOTA, the neural network's weight parameter is optimized using the Sea Lion optimization (SLO).The proposed QPET-SOTA-SLO applied in MATLAB/Simulink platform. The proposed method was calculated using performance measures like accuracy, precision, sensitivity, computation time, and recall. Higher accuracy of 16.65%, 18.85%, and 17.89%, as well as higher sensitivity of 16.34%, 12.23%, and 18.54%, are achieved by the suggested QPET-SOTA-SLO approach. In comparison to the current approach, there are 14.89%, 16.89%, and 18.23% as well as 82.37%, 94.47%, and 87.76% less computing time.