8 min read
The telecommunications industry is on the verge of a major transformation through the use of advanced analytics and big data technologies like the MapR Data Platform. The MapR Guide to Big Data in Telecommunications is designed to help you understand the trends and technologies behind this data driven telecommunications revolution. Download your complimentary copy here.
With the rapid expansion of smart phones and other connected mobile devices, communications service providers (CSPs) need to rapidly process, store, and derive insights from the diverse volume of data travelling across their networks. Big data analytics can help CSPs improve profitability by optimizing network services/usage, enhancing customer experience, and improving security. According to McKinsey, the potential for Telcos to profit from applying data science effectively is substantial. Examples include:
Telecommunication companies collect massive amounts of data from call detail records, mobile phone usage, network equipment, server logs, billing, and social networks, providing lots of information about their customers and network, but how can telecom companies use this data to improve their business?
Most telecom use cases fall into these main categories: customer acquisition and retention, network services optimization, and security.
Data-Driven Improvement of Services or Product
Telecoms need to share data between cell towers, users and processing centers and due to the sheer volume of this data, it is important to process it near the source and then efficiently transfer it to various data centers for further use. MapR Event Store, a new distributed messaging system, is uniquely effective to transport huge amounts of data and to make this data available with reliable geo-distributed replication across multiple data centers. With MapR Event Store, you can replicate streams in a master-slave, many-to-one, or multi-master configuration between thousands of geographically distributed clusters.
One MapR customer is utilizing MapR Event Store to collect real-time data from all of its regional data centers and bring it to the HQ Central Data Center.
Before, the customer was using FTP to transfer data from antennas to regional data centers and to the HQ Central Data center, but the FTP transfer meant extreme latency throughout the data pipeline.
Now data is collected at regional data centers with MapR Event Store and made available in real time to regional dashboards.
MapR Event Store Topics at regional data centers are replicated in a many-to-one configuration to the HQ Central Data Center, making events available in real time to the HQ dashboard. This means they can now monitor global performance and react fast enough to improve customer services.
Being able to process high throughput geo-distributed events in real time enables:
Analyzing these events in real time is the key to timely insights on network services in order to improve customer satisfaction.
Using data science in order to better understand and predict customer behavior is an iterative process, which involves:
Data Discovery and Model Creation:
Analysis of historical data.
Knowing and applying the right kind of machine learning algorithms to get value out of the data.
Using the Model in production to make predictions
Data Discovery and updating the Model with new data.
In order to understand the customer, a number of factors can be analyzed such as:
With this analysis, telecom companies can gain insights to predict and enhance the customer experience, prevent churn, and tailor marketing campaigns.
The architecture below shows how batch processing on different data sources can be used to build and update a model, which can then be used for real-time predictions on streaming data.
Solutionary, a subsidiary of NTT Group, is a leader in Managed Security Services. They provide Threat Intelligence, Incident Response, Compliance and Vulnerability Management as a service to their clients. Their platform collects and correlates vast amounts of data from logs, endpoints, firewalls, and network devices.
They needed to improve scalability as the data volume grew, but it was cost-prohibitive with their existing Oracle database solution. The old solution could not process the unstructured log data at scale and there were also major performance issues.
They replaced their RDBMS solution with the MapR Data Platform to achieve scalability while still meeting reliability requirements. Their new solution combines machine learning algorithms, complex event processing, and predictive analytics to detect real-time security threats.
All of the components of the use case architectures we just discussed can run on the same cluster with the MapR Data Platform, which provides advantages such as:
Telecom is a classic example of the big data issues of huge volume and velocity of data flow, but CSPs also have high requirements for quick responses to events, security, and reliability. The use cases we just went over showed how telecom companies can not only address these requirements, but also profit from the huge amount of information in their data to improve their business.
More information and use cases:
Stay ahead of the bleeding edge...get the best of Big Data in your inbox.