The production of oil and natural gas contributes to a significant amount of revenue generation in Malaysia thereby strengthen the country�s economy. The flow assurance industry is faced with impediments during smooth operation of the transmission pipeline in which gas hydrate formation is the most important. It affects the normal operation of the pipeline by plugging it. Gas hydrate is a crystalline structure composed of a network of hydrogen bonds between host molecules of water and guest molecules of the incoming gases under high pressure and low temperature conditions. Industry uses different types of chemical inhibitors in pipeline to suppress hydrate formation. To overcome this problem, machine learning algorithm has been introduced as part of risk management strategies. The objective of this research is to evaluate the various types of machine learning models used to predict the gas hydrate formation where the input parameters are gas composition, pressure and concentration of inhibitor and the output parameter is hydrate deposition/formation temperature (HDFT). Three machine learning models are compared: Artificial Neural Network (ANN), Least Square version of Support Vector Machine (LSSVM), and Extremely Randomized Trees (Extra Trees). Comparison of the three different machine learning models is based on the correlation coefficient, R2. The best choice of machine learning model that has highest R2 is obtained by Extra Trees model of 0.9991 compared to other two machine learning models which predicted R2 value greater than 0.96. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.