Data Science as a Service for Mobile Operators 


At the core of Xona Partners solution, developed in partnership with lead mobile operators, is a highly scalable intelligent real time data analysis computing model, specifically customized to the needs of mobile data analytic. This provides a self adaptive correlation between the various data feeds of the mobile operator’s ecosystem and its business logic and processes. The goal was to derive new revenue generating services for the mobile operator, as well as various optimization models, thereby increasing the competitiveness of the mobile operators.

Four concurrent trends are converging at the moment in the mobile world: novel architecture to store and access big data (Hadoop, MapReduce, etc.), machine learning and mining algorithms that are computationally tractable, leveraging distributed cloud based computing models, and hardware architecture that are increasingly scalable (with regard to selectively and dynamically processing large volumes of data (DPI, layer4-7 SDN, etc.);  finally, the evolution of mobile operators from being providers of access, connectivity and voice/data services to becoming a platform enabling the development of digital lifestyles. It is in fact, the first time ever, that such trends are colliding. This opens up the opportunity to leverage the vast amount of real time subscriber and services data available to the mobile operators, through a correlation of its underlying business processes; also, to optimize its business logic, dynamically derive new revenue streams and upgrade existing modes of operations.

Problem & Approach

As of today, the various business intelligence and data analytics products on the market have the following shortcomings: (1) a limited scalability of the data collection models, (2) a lack of efficient machine learning and predictive modeling algorithms to process collected data in real time, (3) an open loop data analysis feedback, that is not dynamically correlated with the operator’s business logic and (4) a computing and pricing model that is based on centralized localized processing, that is does not take advantage of the pay as you go cloud based computing and pricing models.

Our goal is to address the above shortcomings, by taking advantage of technology innovations that have happened over the last 2 to 3 years, and are just now getting to a sufficient level of maturity to be commercially applicable to mobile data analytics, keeping in mind the mobile operators’ business goals.


Our solution is inherently modular, composed of

(1) A hybrid local/cloud based data gathering and storage, leveraging novel techniques optimized for the variety of data models. Adaptations of Hadoop-like models and their underlying MapReduce computing paradigm for large scale distributed file systems, are leveraged to present the various data sets, that are normally gathered in silos into a common data representation accessible to data processing models and

(2) A set of machine learning and data mining algorithms, specifically focused on clustering and predictive modeling in high dimensional spaces (based on imprecise, uncertain and incomplete information), efficient statistical data summarization and features extraction algorithms as well as large scale real time data streams management.

These tools will be at the core of the processing engine, aimed at deriving optimization to the existing business logic. They will augment it with new revenue generating business logic, which would be mapped to a set of new revenue generating services.

Various use cases are being worked on. They cover several aspects leveraging the data mining logic, to optimize interaction with northbound mobile operators’ APIs, Overlay services mash up, Interaction with real time bidding online ads platforms, analysis of vehicular data off autonomous vehicles, off mobile health monitoring devices, etc.

The various modules described will be at the core of the new business solution that Xona Partners and the mobile operator jointly developed. Moreover, these modules and their visible interfaces are designed so they can be customized to the mobile operators’ needs, and, can be integrated into its existing processes. It is such customization, based on specific use cases, which we aim at through the partnership we are proposing to initiate.

Back to Case Studies