Machine learning brings new methodologies and opportunities to strategic management research. Based on 27 papers published in top international strategic management journals between 1999 and 2022, this paper systematically summarizes four dimensions of machine learning applications in strategic management research: variable measurement, feature selection, model estimation, and causal inference. This paper analyzes representative literature on each dimension, describes the machine learning algorithms, principles, and steps they employ, and explores future directions for strategic management scholars to utilize machine learning for empirical research. It is found that natural language processing techniques and classification algorithm not only improve the accuracy of quantifying key variables, but also enhance the capabilities of variable selection, topic extraction, and pattern recognition, thus deepening the understanding of the object of strategic management research. In addition, machine learning algorithms, such as random forests and support vector machine, have significant application value in improving the validity and robustness of model estimation. Methods such as double lasso, double machine learning, and generalized random forest provide strong technical support for causal inferences. The purpose of this paper is to provide guidance and suggestions for using machine learning techniques to deepen strategic management research, as well as laying a theoretical and methodological foundation for future research and applications in the field of strategic management.