To help during crises in developing countries, researchers from the Data Science Institute and Department of Computing at Imperial College London have developed a new, artificially intelligent algorithm that predicts the gender of pre-paid mobile phone users.
When crises happen, phone tracking technologies can help locate those in need of help. For this reason, they have been used for years, but in developing countries, most phones are pre-paid, meaning they lack key data about the person carrying the phone. Luckily, the new development could help by identifying especially vulnerable groups of people such as women with young children.
The new technology is a machine learning algorithm that can predict the gender of a person using the phone. It was tested using mobile phone data from 10,000 users in a developed and developing country, where it reliably predicted users’ gender based on the way they use their phone. Its accuracy ranged from 74.3 to 88.4% in a developed country and 74.5 to 79.7% in a developing country.
By analyzing pre-paid phone data to locate vulnerable groups of people such as older people or women with potentially young children, the new algorithm could help rescuers find and save more people in crises.
Imperial College London via Phys.org (https://phys.org/news/2017-05-humanitarian-efforts-aided-ai.html)