TY - GEN
T1 - Research on the Evaluation Method of Auxiliary Expert Talents Based on Ensemble Learning
AU - Fan, Yuhang
AU - Xu, Pengjing
AU - Zhu, Yue
AU - Chen, Miao
N1 - Funding Information:
ACKNOWLEDGMENT This study was conducted at Data Science and Artificial Intelligence Institute of Shanghai Science and Technology Innovation Resources Center, supported by STCSM Grands No:21PJ1421300 and No:18510745600..
Publisher Copyright:
© 2022 IEEE.
PY - 2022
Y1 - 2022
N2 - Talent evaluation is an important part for our country to discover outstanding talents, to allocate human resources according to market, to motivate innovation and entrepreneurship. At present, domestic talent evaluation is mostly carried out in the traditional organizational expert mode, and there is huge space for improvement in efficiency and cost. Based on multiple batches of structured candidate talent index data, this study uses an integrated learning model to simulate and predict talent scores, which can assist experts on their work and improve assessment efficiency. Results from our experiments show, even in the case of small data sets, the scoring process based on our model can have the average error about 6 percentage between the predicted score and the actual score, and the error can be further reduced when the amount of data increase.
AB - Talent evaluation is an important part for our country to discover outstanding talents, to allocate human resources according to market, to motivate innovation and entrepreneurship. At present, domestic talent evaluation is mostly carried out in the traditional organizational expert mode, and there is huge space for improvement in efficiency and cost. Based on multiple batches of structured candidate talent index data, this study uses an integrated learning model to simulate and predict talent scores, which can assist experts on their work and improve assessment efficiency. Results from our experiments show, even in the case of small data sets, the scoring process based on our model can have the average error about 6 percentage between the predicted score and the actual score, and the error can be further reduced when the amount of data increase.
KW - ensemble learning
KW - expert decision-making
KW - machine learning
KW - talent evaluation
UR - http://www.scopus.com/inward/record.url?scp=85148623145&partnerID=8YFLogxK
U2 - 10.1109/CIPAE55637.2022.00016
DO - 10.1109/CIPAE55637.2022.00016
M3 - Conference Proceeding
AN - SCOPUS:85148623145
T3 - Proceedings - 2022 International Conference on Computers, Information Processing and Advanced Education, CIPAE 2022
SP - 30
EP - 34
BT - Proceedings - 2022 International Conference on Computers, Information Processing and Advanced Education, CIPAE 2022
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 3rd International Conference on Computers, Information Processing and Advanced Education, CIPAE 2022
Y2 - 26 August 2022 through 28 August 2022
ER -
