This paper presents an overview of tunnelling-induced ground settlement prediction methods, which are important for safe tunnel infrastructure development, using different types of machine learning (ML) algorithms and regression methods. Due to heavy traffic and more construction, soil settlement chances are high during the tunnel construction work. Machine learning algorithms hold significant potential to predict surface settlement due to tunnelling. The study highlights the description of the study sites and collected dataset, machine learning methodologies, introduction to different machine learning methods, and performance evaluation in machine learning. The review study is focused on exploring the application of mainly seven algorithms, namely Artificial Neural Network (ANN), Back-propagation Neural Network (BPNN), General Regression Neural Network (GRNN), Wavelet Neural Network (WNN), Extreme Learning Machine (ELM), Support Vector Machine (SVM) and Random Forest (RF) in predicting tunnelling induced surface settlement. The challenges of ground displacement prediction by different ML algorithms and future research directions have been illustrated.