Image credit: Data Science Institute and department of Computing at Imperial College LondonUsing a newly developed AI algorithm that can accurately identify the gender of a pre-paid cell phone user may expedite help to vulnerable groups like woman and children in an emergency situation, according to researchers.

The algorithm, developed by researchers from the Data Science Institute and Department of Computing at Imperial College London, takes current phone tracking technology a step further by determining identifying information about pre-paid cell phone (widely used in developing countries) users, which is typically not available.

To test the machine learning algorithm, researchers analyzed mobile phone data from 10,000 cell phone users in both a developed country and a developing country. The researchers demonstrated that their algorithm could identify the gender of a prepaid cell phone user with a 74.3 percent to 88.4 percent accuracy in a developed country and a 74.5 percent to 79.7 percent accuracy in a developing country (almost 10 percent higher than in previous studies).

Additionally, researchers were able to identify the approximate age and socio-economic status of users from the data being analyzed.

Inspired by the 2015 earthquake in Nepal where rescue efforts were aided by mobile phone data, researchers hope to apply the algorithm to emergency situations targeting relief efforts to women with small children and older people susceptible to disease who are often vulnerable in a crisis.

Dr. Yves-Alexandre de Montjoye, the lead author on the study from Imperial's Data Science Institute and Department of Computing, said: "It is crucial to investigate how AI might help us mitigate some of the devastating effects of the world's worst crises. Imagine if we could have used this technology in the aftermath of the Nepal crisis. We could have located refugee populations in search of help and determined who might've been the most vulnerable and needed assistance first."

The next step for the team involves extending their work to other locations and deploying it in the field, while protecting the privacy of users. They aim to work with other organizations such as the OPAL project.

The study is published in the journal EPJ Data Science.