Over the past decade, we have witnessed an enormous amount of research effort dedicated to the design of efficient outlier detection techniques while taking into consideration efficiency, accuracy, high-dimensional data, and distributed environments, among other factors. In this article, we present and examine these characteristics, current solutions, as well as open challenges and future research directions in identifying new outlier detection strategies. We propose a taxonomy of the recently designed outlier detection strategies while underlying their fundamental characteristics and properties. We also introduce several newly trending outlier detection methods designed for high-dimensional data, data streams, big data, and minimally labeled data. Last, we review their advantages and limitations and then discuss future and new challenging issues.