AI Case Study
Alto Data Analytics identifies and evaluates unsafe sanitation around the world with image recognition technology
Alto Data Analytics leveraged AI image recognition technology to analyse open source images of living conditions according to income levels around the world from 'Dollar Street'. The aim of their project was to present the global water crisis around the water based on hygiene and sanitary conditions in which people live. Based on the system capabilities of recognising toilet facilities, the research revealed that toilets from low-income families are less recognisable and suggested that 30-50% of the world's population are likely to living in unsafe sanitary conditions.
Public And Social Sector
"Last summer, Alto Analytics, a company dedicated to helping organizations understand the world with data and artificial intelligence, took on this challenge to help understand the global water crisis in support of World Toilet Day.
Our data science team used open data from Dollar Street – a project developed by Gapminder to improve people's understanding of inequality, with a website of images of living conditions and belongings from real families around the world, organized by income levels.
Alto’s analysts modelled an AI-powered image recognition analysis of toilets, for an automated and faster way to find a more exact number of people impacted by unsafe sanitation conditions on a global scale. Alto’s team processed 971 Dollar Street images of toilets to test the ability of the algorithm to identify toilets according to income groups. They then used Gapminder tools to analyse the data for a clearer understanding of what proportion of the global population is using unsafe sanitary facilities.
This revealed that 30.3% of the world’s toilets cannot be recognized by artificial intelligence, based on the images available on gapminder.org. Alto analysts found a direct correlation between AI results and family income, as the algorithm struggled to identify toilets from low-income families.
Our data science team then collated images that were recognized by the algorithm and those that were not and plotted results by income levels.
Toilets of families with an income of less than $122.50 per month were not recognized by the AI, representing 30.3% of the world’s total population, 2.22 billion people.
Toilets of families with an income of less than $245 had a 50% chance of being recognized. These families represent 47.8% of the world’s population, 3.42 billion people.
Our analysis was based on Gapminder’s dataset alone, but these estimates are closely aligned with UN data. What makes Alto’s insights powerful is that they can be updated in real-time, as new photos are constantly uploaded to Gapminder and Dollar Street, providing an automated and real-time method to evaluate unsafe sanitation worldwide.
"The poorest families in the data did not have access to a distinguishable toilet."
"Today, data is generated in profound volumes and, as the era progresses, data is no longer solely considered a commodity by companies who can leverage it, but a fundamental catalyst to solve some of the world's most complex social issues.
With reams of public data and open-source artificial intelligence at our fingertips, the challenge for businesses does not lie in access to data, but in how to use data creatively to stay competitive, innovative and philanthropic."