Classifying Online Dating Profiles on Tinder using FaceNet Facial Embeddings

TL;DR

This paper presents a method using FaceNet facial embeddings to classify Tinder profiles based on user preferences, achieving up to 73% accuracy with limited profile reviews.

Contribution

It introduces a personalized classification approach leveraging FaceNet embeddings for online dating profile assessment, demonstrating effective accuracy with minimal user data.

Findings

Logistic regression achieved 65% validation accuracy with 20 profiles.

Model accuracy plateaued around 73% after reviewing 80 profiles.

FaceNet embeddings effectively capture facial features related to attractiveness.

Abstract

A method to produce personalized classification models to automatically review online dating profiles on Tinder is proposed, based on the user's historical preference. The method takes advantage of a FaceNet facial classification model to extract features which may be related to facial attractiveness. The embeddings from a FaceNet model were used as the features to describe an individual's face. A user reviewed 8,545 online dating profiles. For each reviewed online dating profile, a feature set was constructed from the profile images which contained just one face. Two approaches are presented to go from the set of features for each face, to a set of profile features. A simple logistic regression trained on the embeddings from just 20 profiles could obtain a 65% validation accuracy. A point of diminishing marginal returns was identified to occur around 80 profiles, at which the model accuracy of 73% would only improve marginally after reviewing a significant number of additional profiles.