In this paper, we develop a simple and efficient methodology for riding patterns recognition based on a machine learning framework. The riding pattern recognition problem is therefore formulated as a classification problem aiming to identify the class of the riding situation using data collected from three-accelerometer and three-gyroscope sensors mounted on the motorcycle. These measurements constitute experimental database which is valuable to analyze and understand Powered Two Wheelers (PTW) rider behavior. Six well known machine learning techniques are used and applied: the Gaussian mixture models (GMMs), k-Nearest Neighbors (k-NN), Support Vector Machines (SVMs), Random Forests (RFs) and the Hidden Markov Models (HMMs) in both (discrete and continuous) cases. The HMMs are widely applied for studying time series data which is the case of our problem. The data preprocessing consists of filtering, normalizing and manual labeling in order to create the training and testing sets. The experimental study carried out on a real dataset shows the effectiveness of the proposed methodology and more particularly of the HMM approach to perform such riding pattern recognition. These encouraging results work in favor of developing such methodologies in the context of naturalistic riding studies (NRS).