AI Model 'Life2vec' Predicts Life Events with High Accuracy

Developed by a team of international researchers, the model uses large amounts of data to predict outcomes such as personality and time of death, raising ethical questions about data privacy and bias.

Researchers from the Technical University of Denmark, University of Copenhagen, ITU, and Northeastern University in the US have developed an AI model, dubbed 'life2vec', that can predict events in people's lives, including estimating the time of death, with high accuracy.
The model was trained using large amounts of data about people's lives and uses 'transformer models', similar to ChatGPT, to process language and systematically organize the data.
The life2vec model was tested on health data and labor market data for 6 million Danes, and it outperformed other advanced neural networks in predicting outcomes such as personality and time of death.
The researchers emphasize that while the model opens up important perspectives, it also raises ethical questions surrounding the protection of sensitive data, privacy, and the role of bias in data.
The researchers plan to incorporate other types of information, such as text and images or information about our social connections, into the model in the future.