A SHORT EXCERPT FROM THE ARTICLE CAN BE FOUND HERE:
We have developed a method for detecting anomalies on multidimensional time series data and combined this with clusters from news articles to automatically identify potential risks to businesses. To do this, we collect data such as the number of articles, number of positive and negative articles, and share value. These data sets are then combined using data merging, resulting in a single time series data set. We then performed anomaly detection with this data set to find relevant outliers. In parallel, we found news clusters with a set of news articles related to a real world event. For each of these clusters, we extracted relevant keywords and compared them to a predefined list. The keywords in this predefined list are then associated with a specific risk so that we can find potential risks within the clusters. Finally, we combined the results of the previous two steps and overlaid the timestamps of the anomalies with the time span of the cluster. If a cluster containing a risk now overlaps with the timestamp of an anomaly, we conclude that the risks can be considered “real” risks. In the future, we plan to expand the approach to include a trend analysis to determine the probability of risks occurring. In addition, a warning mechanism will be added to the system to enable early detection of potential risks and allow the risk owner to take countermeasures.