Anticipation of service access experience quality problems in communication networks and root cause recommendations

摘要

Embodiments of the present invention use advanced statistical data analysis to anticipate and give recommendations for root cause analysis of service access QoE issues in networks such as 3G / 4G networks. Using FCAPS data as a predictor variable, certain embodiments are configured to set the problem as a predictive regression or classification problem to estimate the service access QoE related indicator. Some embodiments also perform training and tuning of various non-linear statistical modeling algorithms using network deregistration information from the RAN log, eg, based on tree and ensemble methods. [Selection] Figure 2