Predictive analysis of real-time strategy games using graph mining

"Machine learning and computational intelligence have facilitated the development of recommendation systems for a broad range of domains. Such recommendations are based on contextual information that is explicitly provided or pervasively collected. Recommendation systems often improve decision-making or increase the efficacy of a task. Real-Time Strategy (RTS) video games are not only a popular entertainment medium, they also are an abstraction of many real-world applications where the aim is to increase your resources and decrease those of your opponent. Using predictive analytics, which examines past examples of success and failure, we can learn how to predict positive outcomes for such scenarios. To do this, one way to represent this type of data in order to model relationships between entities is by using graphs. The vast amount of data has resulting in complex and large graphs that are difficult to process. Hence, researchers frequently employ parallelized or distributed processing. But first, the graph data must be partitioned and assigned to multiple processors in such a way that the workload will be balanced, and inter-processor communication will be minimized. The latter problem may be complicated by the existence of edges between vertices in a graph that have been assigned to different processors. One objective of this research is to develop an accurate predictive recommendation system for multiplayer strategic games to determine recommendations for moves that a player should, and should not, make which can provide a competitive advantage. Another objective is to determine how to partition a single undirected graph in order to optimize multiprocessor load balancing and reduce the number of edges between split subgraphs"--Abstract, page iv.

Name thesis:degree_name

Ph. D. in Computer Science

Grantor

Missouri University of Science and Technology

Author dc:creator

• Alobaidi, Isam Abdulmunem

• Data mining
• Graph mining
• Graph partitioning
• Hotspot
• Predictive analytics
• Recommendation systems
• Computer Sciences

Repository record dc:identifier

https://scholarsmine.mst.edu/doctoral_dissertations/2824

OAI identifier oai:identifier

oai:scholarsmine.mst.edu:doctoral_dissertations-3829