In most of the United States, an individual with an annual income of $12,760 or less is classified as living below the poverty line. Though the share of the population living on such low incomes has fallen considerably in recent years, there are still 43.5 million Americans living in poverty – a number that will likely climb with the crippling effects of the ongoing COVID-19 pandemic. However, recently mathematicians have used machine learning to develop a new model for measuring poverty in different countries that challenges the concept of a fixed ‘poverty line’. This interesting news came to us from EurekAlert! in their article, “‘Poverty line’ concept debunked by new machine learning model.”
The study by academics at Aston University suggests mainstream thinking around poverty is outdated because it places too much emphasis on subjective notions of basic needs and fails to capture the full complexity of how people use their incomes.
Their new model uses computer algorithms to synthesize vast amounts of spending and economic data. This approach has the potential to help policymakers worldwide predict future poverty levels and inform any planning towards alleviating the problem.
Melody K. Smith
Sponsored by Data Harmony, a unit of Access Innovations, the world leader in indexing and making content findable.
