A Novel Similarity-Based Link Prediction Approach for Transaction Networks

Abstract

A network consists of nodes and links, which represent components of a system and interactions between them, respectively. An example of networks is transaction networks, in which nodes and links represent firms and transactions, respectively. Link prediction in transaction networks is an important problem, which aims to estimate the likelihood of a transaction between two firms. It can be used to predict missing link information between firms to gain fuller knowledge as transaction information is not easily accessible between firms. In addition, firms can use it to predict future transactions as transactions evolve over time for various reasons such as a shift in customer demand, resource availability, etc. Many link prediction methods have been proposed for networks. However, to the best of our knowledge, there is no existing link prediction method for transaction networks. Existing methods are not suitable for transaction networks as they assume homophily, the tendency of individuals to associate with similar others, which may not be true in transaction networks. In addition, they do not consider the hierarchy structure exhibited in transaction networks. In this article, we propose a new similarity score for transaction networks that account for multiple, temporal, and directed transactions. We then propose a link prediction procedure based on the proposed similarity score to predict new transactions in transaction networks, which avoids the homophily assumption and exploits the hierarchical structure of transaction networks. The proposed method is tested on real-world transaction networks and yields better area under the receiver operating characteristic curve compared to existing methods.