Researchers have discovered another possibility for artificial intelligence (AI) that, while intriguing, may not be as fun as previous discoveries about the technology.
A recent study in Nature Computational Science suggests that a new AI system that treats human life like a language might be able to accurately predict death over a specific period, among other details of life.
As part of their research, Danish researchers developed a machine learning model called life2vec, which can predict details of people’s lives, including death, international moves, and personality traits.
The model uses data from millions of residents, including dates of birth, gender, employment, location, and use of the country’s general healthcare system.
Over four years, the model was more than 78% accurate in predicting mortality, outperforming other forecasting methods such as actuarial tables and machine learning tools.
Life2vec showed early promising signs of a link between personality traits and life events, with 73% accuracy in predicting people’s moves from Denmark and self-reported responses to a personality questionnaire in a separate test.
The study demonstrates an exciting new approach to predicting and analyzing people’s life trajectories, said Matthew Salganik, a professor of sociology at Princeton University who studies computational social sciences.
The life2vec developers “are using a completely different style that, as far as I know, no one has used before,” he says.
Lehmann and his team developed a language processing tool called life2vec that can predict people’s futures by processing individuals’ data into unique timelines of events such as salary changes and hospital admissions.
Read Also: TikTok Unveils Election Integrity Measures Addressing Hate Speech and Disinformation for Feb 8 Polls
The flexible architecture of the model allows for easy optimization and tuning and provides predictions on many unexplored aspects of human life, making life2vec a promising tool for future predictions.
Lehmann says health professionals have already contacted him, asking for help developing health-focused versions of life2vec, including one that could, for example, shed light on population-level risk factors for rare diseases.
He plans to use a tool to uncover hidden societal biases, such as unexpected links between career progression and age or country of origin, to explore the impact of relationships on quality of life and salary, and to expose hidden societal biases to laypeople.
