Gamification based Skill Prediction using Blockchain Technology

Abstract

Skill prediction is the process of withdrawing information from existing data for the purpose of determining their existing skills and future trends. Player gameplay data are collected from various sites and it is validated using blockchain technology. This ensures that the chain remains immutable, because any change in a block’s data will invalidate every block that follows it. Players are then clustered using the K-means clustering algorithm, a clustering approach based on partitions is implemented. To increase the accuracy of prediction, players are classified into groups. Euclidean distance is computed to measure the distance or the (dis)similarity between each pair of players. Decision tree algorithm is used to predict player skill. The efficiency of the proposed method can be assessed using the measures such as precision, recall, F-Score, correlation of Matthews and Fallout rate. The proposed system improves the performance of the system as well as predict more accurate skill using kmeans clustering and decision tree.