“Are you ever worried your friends aren’t being honest with you about your taste in fashion?”

Are you ever worried your friends aren’t being honest with you about your taste in fashion? Well now you can turn to a computer in order to have your suspicions confirmed, or not, as the case may be. Don’t be downcast if it turns out your outfits are not de rigeur, however — the software can also help you plan a Cher from Clueless-style makeover.

Researchers at the University of Toronto have developed an algorithm that uses a combination of computer vision and machine learning to help you identify exactly where you are going wrong, by comparing you against a range of “fashionability factors”. The fashionability factors that images are compared against obviously do include the garments the subject is wearing, but also a range of other criteria, such as how appealing the scene behind the person is, how the image was taken, how visually appealing the person is, her/his age.

These have been chosen to ensure a deeper and more complex reading of your fashion sense, rather than judging you by outfit alone. As the researchers put it: “The garment itself being fashionable is also not a perfect indicator of someone’s fashionability as people typically also judge how well the garments align with someone’s ‘look’, body characteristics, or even personality.” So be prepared — this algorithm is not about to hold back.

I am prepared.