Prediction of Employee Promotion Based on Personal Basic Features and Post Features

Abstract

Promotion is the focus of human resource management research. Because there are few researches about the mining of promotion features in existing studies, this paper uses the data of a Chinese state-owned enterprise, constructs a number of features and applies machine learning methods to predict employee promotion. Firstly, we build personal basic features and post features based on five strategies. Secondly, the correlation analysis is conducted to preliminarily explore the associations between some features and promotion. Then, the model learning and testing are carried out. Experimental results show that the random forest model performs best, which verifies the validity of features. Finally, we calculate the Gini importance of each feature to further analyze its influence on staff promotion. It is found that post features have a higher impact on promotion compared with personal basic features. Among all the features, the working years, the number of different positions and the highest department level greatly affect employee promotion.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 29 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.