Recommendations for Achieving Service Levels within Large-scale Resolution Service Networks

A new recommendation framework that addresses the correct and quick resolution of incidents that occur within the complex systems of an enterprise is introduced here. It uses statistical learning to mediate problem solving by large-scale Resolution Service Networks (with nodes as technical expert groups) that collectively resolve the incidents logged as tickets. Within the enterprise a key challenge is to resolve the tickets arising from operational big data (1) to the customers' satisfaction, and (2) within a time constraint. That is, meet the service level (SL) goals. The challenge in meeting SL is the lack of a global understanding of the types of needed problem solving expertise. Consequently, this often leads to ticket misrouting to experts that are inappropriate for solving the next increment of the problem. The solution here proposes a general two-level classification framework to recommend a SL-efficient sequence of expert groups that jointly can resolve an incoming ticket. The experimental validation shows 34% accuracy improvement over existing locally applied generative models. Additionally, recommended sequences are above 96% likely to meet the enterprise SL goals, which reduces the SL violation rate by 29%. Recommendations are suppressed in the case of non-routine content which is automatically flagged for special attention by humans, since here the humans outperform statistical models.