An Adaptive Rule-Based Approach to Resolving Real-Time VoIP Wholesale Billing Disputes

摘要

The Voice over Internet Protocol (VoIP) industry has grown immensely since its inception, and is predicted to grow at double the rate in the coming years. The growth of the VoIP industry has made significant contributions to the economy, and has also increased the volume of data, which is a challenge for processing. VoIP security vulnerabilities and lack of appropriate tools and infrastructure can lead to billing disputes and fraud attacks, impacting VoTP wholesalers' profits. To reduce economic losses, these challenges need to be addressed in a comprehensive and efficient way. This study proposes an intelligent and adaptive rule based reconciliation process to resolve real-time billing disputes with minimal revenue loss. Real-time disputed Call Detail Records are analyzed to generate adaptive rules to cater for dynamic data sources. These rules are used to classify the Call Detail Record into six categories. A summarized report is generated at the end of the analysis that can be used to come to a better resolution during the billing dispute negotiation process. The complexity and volume of data affects the execution time of reconciliation processes. Spark, a distributed processing framework, is used to reduce execution times. The distributed processing solution has reduced execution times by 81.8% on average as compared to non-distributed solutions. The performance of the proposed solution is evaluated against the CALLS Dispute management system (an Aiztek Technologies solution), and the proposed solution has detected 38% more billing disputes in less time as compared to the existing solution.