Use of call detail records in Big Data for development
In 2017, the number of mobile users in the world amounts to 4.9 billion, which means that 66% of the world’s population already has a mobile. The world is eminently mobile and the trend continues. For each call that is made from a mobile phone, a collection of information called Call Detail Record (CDR) is stored. CDR is a valuable source of information that can be used for different business oriented and social oriented purposes. Remarkably useful information on human behaviour may be derived from large sets of de-identified CDRs, such as, mobility, social interaction or economic activity.
Within the scope of the mobility, we can find different types of patterns, from local mobility to migratory movements. Sudden changes in mobility patterns of vulnerable groups can indicate exposure to new shocks such as floods, loss of employment opportunities or adverse weather patterns.
Big Data for development
Big Data is a term that initially describes the large amount of data that flood our daily lives . However, what matters in Big Data is what we can be do with data, it can be analysed to get ideas that lead to better decision.
The basis for the most used definition of big data are the three V :
- Volume: Large amounts of data.
- Velocity: Large amounts of data from transactions with high refresh rate resulting in data streams coming at great speed.
- Variety: Data come from different data sources and in various formats.
Big data is high-volume, high-velocity and/or high-variety information assets that demand cost-effective, innovative forms of information processing that enable enhanced insight, decision-making, and process automation.
Data can provide snapshots of the well-being of populations at high frequency, high degrees of granularity, and from a wide range of angles, narrowing both time and knowledge gaps. Analysing this data may help discover anomalous changes in how communities access services, that may serve as proxy indicators of changes in underlying well-being. Real-time awareness of the status of a population and real-time feedback on the effectiveness of policy actions should lead to a more agile and adaptive approach to international development, and ultimately, to greater resilience and better outcomes.
There are various potential applications of Big Data for Development as :
- Early warning: “early detection of anomalies in how populations use digital devices and services can enable faster response in times of crisis”.
- Digital awareness: “big data can paint a fine-grained and current representation of reality which can inform the design and targeting of programs and policies”.
- Real-time feedback: “monitoring a population in real time makes possible to understand where policies and programs are failing and make adjustments”.
Big Data for Development has many definitions but one that is used most often refers to the analysis of millions of data sets to help policy makers take smart decision . For policy makers, development practitioners and other professionals working in international development, data gathering and analytics applications are opening previously unthinkable opportunities to understand, predict and solve the most pressing issues of the developing world.
Call detail records
A Call Detail Record (CDR) provides metadata on how a specific phone number and/or user is utilizing the phone system . This metadata typically includes: when the call took place, how long the call lasted, who called whom, what kind of call was made and how much the call costed.
An additional piece of information that is recorded in CDRs by a mobile network operator is to which cell towers the caller and recipient’s phones were connected at the time of the call . Because the mobile network operator knows the locations of their cell towers, it is possible to use CDRs to approximate the location of both parties. This geospatial information is extremely useful for humanitarian and development applications.
CDRs have the potential to reveal personal information, so the records need to be altered in several important ways before being shared with third parties for analysis. Consequently, by the time CDRs are shared, they look something like this:
Remarkably useful information on human behaviour may be derived from large sets of anonymized CDRs. From the point of view of big data from development, there are at least three dimensions that can be measured:
- Mobility: As mobile users send and receive calls and messages through different cell tower, is it possible to reconstruct the movement patterns of a community.
- Social interaction: The geographic distribution of one’s social connections may be useful for both building demographic profiles of aggregated call traffic and understanding changes in behaviour.
- Economic activity: Monitoring airtime expenses, which is the amount of money spent during a connection to the network, for trends and sudden changes could prove useful for detecting the early impact of an economic crisis, as well as for measuring the impact of programmes designed to improve livelihoods.
- PowerData, Especialistas en Gestión de Datos.” Big Data: ¿En qué consiste? Su importancia, desafíos y gobernabilidad”. Website: http://www.powerdata.es/big-data.
- Xiaomeng Su. “Introduction to Big Data”. Norwegian University of Science and Technology (NTNU). Website: https://www.ntnu.no/iie/fag/big/lessons/lesson2.pdf
- Mark A. Beyer and Douglas Laney. “The Importance of ‘Big Data’: A Definition”. Gartner, 2012
- Global Pulse. “Big Data for Development: Challenges & Opportunities”. May 2012
- Emmanuel Letouzé. “Big Data for Development: What May Determine Succes of failure?”. October 2012
- Mariela Machado. “Applications of Big Data for Development”. Engineering for change. July 2016. Website: https://www.engineeringforchange.org/news/applications-of-big-data-fordevelopment/.
- “What Are Call Detail Records (CDRs)?”. Website: https://www.onsip.com/blog/what-are-call-detail-records-cdrs
- Global Pulse. “Mobile Phone Network Data for Development”. October 2013