Business Intelligence is applied to improve decision making in organizations, and as globalized trading and connectivity increase, the pace and unpredictability of the business environment increase as well. Therefore traditional methods of user-driven data discovery will be too slow, and traditional long-term forecasting methods will be unreliable since the environment is behaving chaotically. For business users and their organizations this means that the ability to act swiftly based upon changes in the environment is the key determining factor for success and failure. The ability to react fast to changes in the environment can be achieved by pursuing two objectives: First, the speed with which a user travels through the four phases of Observation, Orientation, Decision and Action (OODA) can be increased, and secondly the time-horizon for the warnings can be expanded by applying so-called Sentinels.
Sentinels represent schema level relationships between changes over time in certain measures in a multi-dimensional data cube. Sentinels notify users based on previous observations, e.g., that revenue might drop within two months if an increase in customer problems combined with a decrease in website traffic is observed. Hereby, we expand the window of opportunity for organizations and facilitate successful navigation even though the world behaves chaotically. Since sentinel rules are at the schema level as opposed to the data level, and operate on data changes as opposed to absolute data values, we are able to discover strong and useful sentinel rules that would otherwise be hidden when using alternative methods such as sequential pattern mining or correlation techniques.
In this research project we develop so-called mining algorithms for discovering sentinels. At this stage, a sentinel mining algorithm has already been developed and implemented in the business intelligence offering of TARGIT A/S. For more information please see the homepage of TARGIT’s CTO, Morten Middelfart.