# Photofeeler-D3: A Neural Network with Voter Modeling for Dating Photo Impression Prediction

## TL;DR

Photofeeler-D3 is a convolutional neural network that accurately predicts dating photo impressions and facial attractiveness by modeling voter behavior, outperforming previous methods and utilizing a large dataset.

## Contribution

This paper introduces Photofeeler-D3, the first CNN that models voter behavior for improved dating photo impression prediction and facial beauty assessment.

## Key findings

- Achieves accuracy comparable to 10 human votes.
- State-of-the-art performance on DPIP and FBP tasks.
- Leverages over 1 million images and tens of millions of votes.

## Abstract

In just a few years, online dating has become the dominant way that young people meet to date, making the deceptively error-prone task of picking good dating profile photos vital to a generation's ability to form romantic connections. Until now, artificial intelligence approaches to Dating Photo Impression Prediction (DPIP) have been very inaccurate, unadaptable to real-world application, and have only taken into account a subject's physical attractiveness. To that effect, we propose Photofeeler-D3 - the first convolutional neural network as accurate as 10 human votes for how smart, trustworthy, and attractive the subject appears in highly variable dating photos. Our "attractive" output is also applicable to Facial Beauty Prediction (FBP), making Photofeeler-D3 state-of-the-art for both DPIP and FBP. We achieve this by leveraging Photofeeler's Dating Dataset (PDD) with over 1 million images and tens of millions of votes, our novel technique of voter modeling, and cutting-edge computer vision techniques.