Smart Advertisement for Maximal Clicks in Online Social Networks Without User Data

TL;DR

This paper introduces a user-data-independent method for maximizing ad CTR in social networks by using NLP to extract concepts and applying optimization algorithms to select the best combination of these concepts, achieving near-optimal results.

Contribution

It presents a novel approach that predicts CTR without user data by leveraging NLP-extracted concepts and formulates the selection as an optimization problem solved by greedy and genetic algorithms.

Findings

Decision Tree and Random Forest regressors perform best in CTR prediction.

The optimization problem is likely NP-hard, but near-optimal solutions are achievable.

Concepts like politics, celebrity, and organization are highly influential.

Abstract

Click-through rate (CTR) prediction of advertisements on online social network platforms to optimize advertising is of much interest. Prior works build machine learning models that take a user-centric approach in terms of training -- using predominantly user data to classify whether a user will click on an advertisement or not. While this approach has proven effective, it is inaccessible to most entities and relies heavily on user data. To accommodate for this, we first consider a large set of advertisement data on Facebook and use natural language processing (NLP) to extract key concepts that we call conceptual nodes. To predict the value of CTR for a combination of conceptual nodes, we use the advertisement data to train four machine learning (ML) models. We then cast the problem of finding the optimal combination of conceptual nodes as an optimization problem. Given a certain budget $k$, we are interested in finding the optimal combination of conceptual nodes that maximize the CTR. A discussion of the hardness and possible NP-hardness of the optimization problem is provided. Then, we propose a greedy algorithm and a genetic algorithm to find near-optimal combinations of conceptual nodes in polynomial time, with the genetic algorithm nearly matching the optimal solution. We observe that Decision Tree Regressor and Random Forest Regressor exhibit the highest Pearson correlation coefficients w.r.t. click predictions and real click values. Additionally, we find that the conceptual nodes of "politics", "celebrity", and "organization" are notably more influential than other considered conceptual nodes.