As ever new sensor solutions are invading people’s everyday lives and business processes, the use of the signals and events provided by the devices poses a challenge. Innovative ways of handling the large amount of data promise an effective and efficient means to overcome that challenge. With the help of complex event processing and predictive techniques, added value can be created. While complex event processing is able to process the multitude of signals coming from the sensors in a continuous manner, predictive analytics addresses the likelihood of a certain future state or behavior by detecting patterns from the signal database and predicting the future according to the detections.

As to the transportation and logistics domain, processing the signal stream and predicting the future promises a big impact on the operations because the transportation and logistics sector is known as a very complex one. The complexity of the sector is linked with the many stakeholders taking part in a variety of operations and the partly high level of automation often being accompanied by manual processes. Hence, predictions help to prepare better for upcoming situations and challenges and, thus, to save resources and cost. The present paper is to investigate the prevalence of complex event processing and predictive analytics in logistics and transportation cases in the research literature in order to motivate a subsequent systematic literature view as the next step in the research endeavor.