Computer can see inside the human mind

Researchers at the Swiss Federal Institute of Technology in Zurich (ETH), the University of Zurich (UZH) and Columbia University have worked together to develop a new computer model. This is able to predict what decisions people might make in certain situations. According to the ETH, it can forecast with high accuracy which food someone in a supermarket will choose to buy, for example. “With this model, we can practically see inside the human mind and predict decision behavior,” explained Rafael Polanía, Professor of the Decision Neuroscience Lab at the ETH.

The basis for the researchers’ model is a subjective valuation structure stored in the brain. In this structure, preferences for every food are stored based on previous experience and memories. The brain’s internal valuation system depends on context: when going grocery shopping, for instance, this means that our brain efficiently aligns to the respective supermarket. This valuation system relieves the burden on the brain. Sense organs, such as the eyes, ears, nose and mouth, that are attuned to the external world mean the brain is constantly taking in more information than it can process.

These individual valuations add up to an overall preference distribution that can be mathematically explained and evaluated, the ETH explains. This is where the researcher’s model comes in: it makes accurate predictions based on this distribution of valuations and efficiency principles.

The researchers have already tested and calibrated the model using valuations from a pool of test subjects. “The new model accurately predicts which food the test subject will choose in the vast majority of cases,” says Polanía, “and also how often you will change your mind”.

This model has the potential to support marketing and economists could use it for calculating prices more accurately. It could also be used to understand certain aspects of people’s health. “These decisions are also based on subjective valuations, such as how healthy a person thinks a certain product is,” explains Polanía. It is currently working on integrating this criterion into the model. The objective is to discover how people make decisions about their diet, which in turn has implications for obesity or eating disorders like anorexia.