Call Details Record Analysis: A Spatiotemporal Exploration toward Mobile Traffic Classification and Optimization

Abstract

The information contained within Call Details records (CDRs) of mobile networks can be used to study the operational efficacy of cellular networks and behavioural pattern of mobile subscribers. In this study, we extract actionable insights from the CDR data and show that there exists a strong spatiotemporal predictability in real network traffic patterns. This knowledge can be leveraged by the mobile operators for effective network planning such as resource management and optimization. Motivated by this, we perform the spatiotemporal analysis of CDR data publicly available from Telecom Italia. Thus, on the basis of spatiotemporal insights, we propose a framework for mobile traffic classification. Experimental results show that the proposed model based on machine learning technique is able to accurately model and classify the network traffic patterns. Furthermore, we demonstrate the application of such insights for resource optimisation.

ECMCRR-MPDNL for Cellular Network Traffic Prediction With Big Data

“…But the performance of the deep learning was not improved by considering different traffic patterns. A clustering-based artificial neural network (C-ANN) model was introduced in [15] for classifying the mobile traffic patterns. Though the model increases the accuracy, the false positive rate was not minimized.…”

Orthogonal projection for anomaly detection in networking datasets

“…In addition, frameworks can be used to examine data from other perspectives, such as gendered urban mobility like in Gauvin et al (2020); to extract other parameters like forensic analysis as in Abba et al (2019) or the activities of the base stations in a mobile cellular network (Jiang et al 2020). Recently, many machine learning techniques are included in frameworks oriented to analyze and classify the information of a CDR (Sultan et al 2019) or to apply it to concrete areas like churn prediction (Ahmad et al 2019;Garimella et al 2021).…”

“…In order to increase the efficiency of anomaly detection, the addition of network information metadata to the geographic coordinates provided by the CDR database offers an interesting mechanism to improve the precision of the data, revealing particular behaviours of the network. Furthermore, most proposed network-collected data analysis techniques in the literature (Garroppo and Niccolini 2018;Zhu and Sun 2020;Sultan et al 2019) lows on examining a single parameter or the sum of the set of characteristics, so the inclusion of additional information about a particular area should lead to a greater understanding of it and can be extracted through its analysis. With this view towards future progress, the independent data contained in a CDR can be represented as a set of different features in the form of a data cube to accurately describe the associated geographic area.…”

Forecasting economic result of business logic improvements using Game Theory for modeling user scenarios

“…[11] highlights the efficiency of user behavior modeling in risk assessment of information systems (webbased). Considering the emerging development of mobile devices' utilization, many researchers [12][13][14] are paying significant attention to the mobile sector of the web and new opportunities related to additional data sources and IoT [14][15][16][17]. Like [19][20][21], many authors are focused on practical challenges of behavior modeling for gamification.…”