Network Security Internet Technology Development Database Servers Mobile Phone Android Software Apple Software Computer Software News IT Information

In addition to Weibo, there is also WeChat

Please pay attention

WeChat public account


Danish AI model is more accurate than insurance companies in predicting mortality, causing fears of abuse

2024-05-23 Update From: SLTechnology News&Howtos shulou NAV: SLTechnology News&Howtos > IT Information >


Shulou( Report--, December 19 (Xinhua)-- Suni Lehmann Jorgensen of the Danish University of Science and Technology and his team have developed a powerful artificial intelligence model that can predict mortality based on personal data, far more accurate than any existing model, even those used by the insurance industry. The researchers say the model can warn of health and social problems in advance and needs to be wary of being abused by large companies.

The Tupu Pexels Jorgensen team used a rich data set covering education, medical care, diagnosis, income and occupation of 6 million people in Denmark (2008-2020) to convert it into text that can be used to train large language models. This model is similar to ChatGPT,ChatGPT 's ability to infer the possibility of future events by analyzing large amounts of text data and predicting the next most likely word. Similarly, the "Life2vec" model developed by researchers can analyze the sequence of events in an individual's life course and predict what is most likely to happen next.

In the experiment, the Life2vec model was trained only with data from 2008-2016 and tested from 2016-2020. The researchers divided people between the ages of 35 and 65 into two groups, half of whom died between 2016 and 2020, while the other half survived. The Life2vec model predicts their survival results, which is 11% more accurate than the existing AI model and the mortality statistics commonly used in the insurance industry. noted that the model can also predict the personality test results of a subset of the population more accurately than the AI model, which is specifically used for personality tests. Jorgensen believes that the Life2vec model has absorbed enough data to be applied to a wide range of health and social issues, such as forecasting and early intervention in health problems, or helping governments narrow the gap between rich and poor. However, he also stressed that the model may cause harm if it is abused by enterprises.

"the Life2vec model should not be used by insurance companies," Jorgensen said. "the essence of insurance is to share risks and predict who will encounter misfortune or death, which runs counter to the concept of mutual insurance." But he says similar technologies already exist and could be used by tech giants with large amounts of user data to predict and influence user behavior.

Matthew Edwards of the British Association of Actuaries says insurers are indeed interested in new forecasting methods, but current decisions rely mainly on a simple AI technique called a generalized linear model.

"Insurance companies have been predicting life expectancy by analyzing existing data for hundreds of years," Edwards said. "but since policies can be as long as 20 to 30 years, we are very cautious about adopting the new approach because any major mistake can cause huge losses. although everything is changing, the pace of the insurance industry will slow down because no one wants to make a mistake."

The emergence of Life2vec model highlights the strong potential of artificial intelligence technology in predicting the future, but it also raises important ethical issues. How to ensure that this technology is used to improve people's lives, rather than exacerbating social inequality, is an urgent problem to be solved.

Welcome to subscribe "Shulou Technology Information " to get latest news, interesting things and hot topics in the IT industry, and controls the hottest and latest Internet news, technology news and IT industry trends.

Views: 0

*The comments in the above article only represent the author's personal views and do not represent the views and positions of this website. If you have more insights, please feel free to contribute and share.

Share To

IT Information


© 2024 SLNews company. All rights reserved.