This study presents the runtime behaviour-based classification procedure for Windows malware. Runtime behaviours are extracted with a particular focus on the determination of a malicious sequence of application programming interface (API) calls in addition to the file, network and registry activities. Mining and searching n-gram over API call sequences is introduced to discover episodes representing behaviour-based features of a malware. Voting Experts algorithm is used to extract malicious API patterns over API calls. The classification model is built by applying online machine learning algorithms and compared with the baseline classifiers. The model is trained and tested with a fairly large set of 17,400 malware samples belonging to 60 distinct families and 532 benign samples. The malware classification accuracy is reached at 98%.