Labor Market Prediction Using Machine Learning Methods: A Systematic Literature Review

This study systematically reviews the literature in the field of labor market prediction. The main aim is to identify the most recently applied machine learning methods used to predict the job market's future. A comprehensive search was conducted across multiple databases, including Scopus, Google Scholar, IEEE, and Web of Science, resulting in a final selection of 10 relevant articles published between 2018 and 2023. The findings of this study found that the used machine learning methods are Long Short-Term Memory (LSTM), Bidirectional Long Short-Term Memory (BiLSTM), Long Short-Term Memory-Gated Recurrent Unit (LSTM-GRU), and Autoregressive Integrated Moving Average (ARIMA) besides text mining techniques such as word embedding and sentiments analysis. These findings suggest that, in general, hybrid models have the potential to outperform individual models, especially in the case of multiple types of data. The results of this review also emphasize the importance of using integrated datasets when applying machine learning methods. Another important finding was that the key applications of machine learning in labor market prediction are predicting unemployment, predicting needed educational programs, and predicting market demand. This study contributes to labor market forecasting by providing an extensive synthesis and analysis of the existing literature on the future of the labor market and the use of machine learning methods. However, future research must include qualitative and external factors affecting the prediction of the job market future. The major limitation of this study is the number of reviewed publications.