Researchers say this study shows an exciting new approach to predicting and analyzing people’s life trajectories.
Researchers have uncovered yet another artificial intelligence (AI) capability. While interesting, this may not be as exciting as previous discoveries about this technology.
In recent research, natural computational science A new AI system that treats human life like a language suggests it may be able to accurately predict death within a given period of time, among other details of life.
As part of the study, Danish researchers developed a machine learning model called life2vec that can predict details of people’s lives, including death, international migration, and personality traits.
The model uses data from millions of residents, including date of birth, gender, employment, location, and access to the country’s universal healthcare system.
Over four years, the model was found to be more than 78% accurate in predicting mortality, outperforming other forecasting methods such as actuarial tables and machine learning tools.
Life2vec predicted people’s migration outside Denmark and self-reported responses to personality questionnaires in a separate test with 73% accuracy, showing promising early signs of linking personality traits to life events .
Matthew Salganic, a professor of sociology at Princeton University who studies computational social science, said the study demonstrates an exciting new approach to predicting and analyzing people’s life trajectories.
The developers at life2vec “use a very different style that, to my knowledge, no one has ever used before,” he says.
Lehmann and his team developed a language processing tool called life2vec. The tool can predict people’s futures by processing their data to create unique timelines of events such as salary changes or hospitalizations.
The flexible model architecture allows easy adjustment and fine-tuning, and provides predictions about many unexplored aspects of human life, making life2vec a promising tool for future prediction.
Lehman said medical professionals have already contacted him asking for help developing health-related versions of life2vec. This includes versions that can help understand population-level risk factors for rare diseases, for example.
He uses tools to uncover hidden social biases, such as the unanticipated relationship between occupational advancement and age or country of origin, and examines the impact of relationships on quality of life and pay. At the same time, we plan to uncover hidden social prejudices.