A team of scientists has developed an algorithm that uses an individual's life story to predict how they will live and when they will die.
The study revealed that the accuracy of the model called "life2vec" is approximately 78%, which puts it on par with other algorithms designed to predict similar life outcomes.
Scientists in Denmark and the United States trained the machine learning algorithm on a massive Danish data set, which includes information on more than six million people, including income, occupation and place of residence.
They came up with an innovative model that can process simple language and generate predictions about a person's likelihood of dying early, or their income over their lifetime.
The model was trained on data from 2008 to 2016, and correctly predicted who would die by 2020 in more than three-quarters of cases.
Lead researcher Sonny Lehmann, a professor of networks and complex systems, said the data all came from Denmark, so the predictions may not apply to people living elsewhere, coupled with the fact that most people probably don't want to know when they will die.
He added: "The model opens up important positive and negative points of view to be discussed and dealt with politically."
It is stated that when the model is released to the general public, Danish privacy laws will make it illegal to use life2vec to make decisions about individuals, such as writing insurance policies or making employment decisions.
The study was published in the journal Nature Computational Science.
Source: Daily Mail - Publication date: 25/12/2023 - https://r.rtarabic.com/wmw4
Comments