Short Video-based Advertisements Evaluation System: Self-Organizing Learning Approach

TL;DR

This paper introduces a self-organizing learning framework for evaluating short video advertisements, enabling prediction of user behavior without user profiles by learning optimal neural network structures from raw videos.

Contribution

It presents a novel end-to-end self-organizing approach that automatically determines neural network topology and weights for user behavior prediction on unconstrained short videos.

Findings

Achieves superior performance on in-house dataset

Effectively predicts user behavior without user profiles

Adapts to unconstrained short videos

Abstract

With the rising of short video apps, such as TikTok, Snapchat and Kwai, advertisement in short-term user-generated videos (UGVs) has become a trending form of advertising. Prediction of user behavior without specific user profile is required by advertisers, as they expect to acquire advertisement performance in advance in the scenario of cold start. Current recommender system do not take raw videos as input; additionally, most previous work of Multi-Modal Machine Learning may not deal with unconstrained videos like UGVs. In this paper, we proposed a novel end-to-end self-organizing framework for user behavior prediction. Our model is able to learn the optimal topology of neural network architecture, as well as optimal weights, through training data. We evaluate our proposed method on our in-house dataset. The experimental results reveal that our model achieves the best performance in all our experiments.