Abstarct: Drillstring stuck (or simply "stuck") is a serious and costly problem in oil and gas well drilling operations, leading to project delays, equipment damage, and a significant increase in expenses. While research into the mechanisms of this phenomenon began as early as the 1940s and has continually evolved, this study takes a novel data-driven approach to address this persistent challenge. This research aims to develop an intelligent, machine learning-baxsed system to predict the type and probability of this phenomenon in real-time, displaying the results on the driller's panel for rapid decision-making. The area under study is one of the active oil fields in the south of the country, where operational data was collected from 28 wells. This data included daily drilling reports and mud logging data. Due to its higher resolution compared to daily reports, the mud logging data offered greater potential for accurately modeling the patterns that lead to stuck. To address the challenge of a lack of stuck type labels in the data, a clustering algorithm was utilized. This successfully segregated the stuck events into three categories: wellbore geometry, differential pressure, and well packing. For predicting the probability of occurrence (binary classification), the developed models showed the best performance with the Support Vector Machine (SVM) model using a general Gaussian kernel, achieving a sensitivity of 93% for the stuck class. In predicting the type of stuck (multi-class classification), the Linear Support Vector Machine (LSVM) model was identified as the superior model, demonstrating an overall accuracy of 98%. The general conclusion is that the application of these models in the industry enables the adoption of preventive measures (such as changing drilling parameters) before a catastrophic event occurs. Although the final accuracy of the models was limited by the absence of geomechanical and petrophysical information and the scarcity of mud logging data, a strong foundation was laid for improving the safety and efficiency of drilling operations.