Digital Management Mode of Enterprise Human Resources under the Background of Digital Transformation

Abstract

The development of computer technology promotes the emergence of a large amount of data. How to mine the required information from the massive data has become a problem that needs to be considered by enterprise human resources. In view of the data-based requirements of enterprise human resource management in the era of data, this paper studies the use of decision tree technology for data mining of enterprise employees, and on this basis, uses the improved AdaBoost-c4.5 algorithm to carry out experiments on personnel recruitment in human resource departments. The experimental results show that the performance of the algorithm is relatively stable in five cycles, and reaches 83.27% in the fifth cycle. On this basis, the AdaBoost-c4.5 algorithm is compared with ID3 algorithm and C4.5 algorithm. The results show that the performance of AdaBoost-c4.5 algorithm is improved compared with the two algorithms, and in the specific application of enterprise employee recruitment, it can effectively improve the processing of incomplete data in the case of incomplete data, but when the number of iterations reaches more than 10 times, its accuracy will not be improved. This shows that the performance of this algorithm has reached a critical value. If the number of iterations can be reduced, better results can be obtained. At the same time, through comparison with SOC curve, it is found that AdaBoost-c4.5 algorithm has lower cost and is more operable, which has practical significance in actual personnel recruitment.