Complex Event Processing (CEP) is a novel and promising methodology that enables the real-time analysis of stream event data. The main purpose of CEP is detection of the complex event patterns from the atomic and semantically low-level events such as sensor, log, or RFID data. Determination of the rule patterns for matching these simple events based on the temporal, semantic, or spatial correlations is the central task of CEP systems. In the current design of the CEP systems, experts provide event rule patterns. Having reached maturity, the Big Data Systems and Internet of Things (IoT) technology require the implementation of advanced machine learning approaches for automation in the CEP domain. The goal of this research is proposing a machine learning model to replace the manual identification of rule patterns. After a pre-processing stage (dealing with missing values, data outliers, etc.), various rule-based machine learning approaches were applied to detect complex events. Promising results with high preciseness were obtained. A comparative analysis of the performance of classifiers is discussed.