Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

A Comparative Study on Enhancing Prediction in Social Network Advertisement through Data Augmentation

Qikai Yang, Panfeng Li, Xinhe Xu, Zhicheng Ding, Wenjing Zhou, Yi Nian

TL;DR

This paper contributes to the literature by showing that synthetic data augmentation alleviates the limitations imposed by small or imbalanced datasets in the field of social network advertising.

Abstract

In the ever-evolving landscape of social network advertising, the volume and accuracy of data play a critical role in the performance of predictive models. However, the development of robust predictive algorithms is often hampered by the limited size and potential bias present in real-world datasets. This study presents and explores a generative augmentation framework of social network advertising data. Our framework explores three generative models for data augmentation - Generative Adversarial Networks (GANs), Variational Autoencoders (VAEs), and Gaussian Mixture Models (GMMs) - to enrich data availability and diversity in the context of social network advertising analytics effectiveness. By performing synthetic extensions of the feature space, we find that through data augmentation, the performance of various classifiers has been quantitatively improved. Furthermore, we compare the relative performance gains brought by each data augmentation technique, providing insights for practitioners to select appropriate techniques to enhance model performance. This paper contributes to the literature by showing that synthetic data augmentation alleviates the limitations imposed by small or imbalanced datasets in the field of social network advertising. At the same time, this article also provides a comparative perspective on the practicality of different data augmentation methods, thereby guiding practitioners to choose appropriate techniques to enhance model performance.

A Comparative Study on Enhancing Prediction in Social Network Advertisement through Data Augmentation

TL;DR

This paper contributes to the literature by showing that synthetic data augmentation alleviates the limitations imposed by small or imbalanced datasets in the field of social network advertising.

Abstract

In the ever-evolving landscape of social network advertising, the volume and accuracy of data play a critical role in the performance of predictive models. However, the development of robust predictive algorithms is often hampered by the limited size and potential bias present in real-world datasets. This study presents and explores a generative augmentation framework of social network advertising data. Our framework explores three generative models for data augmentation - Generative Adversarial Networks (GANs), Variational Autoencoders (VAEs), and Gaussian Mixture Models (GMMs) - to enrich data availability and diversity in the context of social network advertising analytics effectiveness. By performing synthetic extensions of the feature space, we find that through data augmentation, the performance of various classifiers has been quantitatively improved. Furthermore, we compare the relative performance gains brought by each data augmentation technique, providing insights for practitioners to select appropriate techniques to enhance model performance. This paper contributes to the literature by showing that synthetic data augmentation alleviates the limitations imposed by small or imbalanced datasets in the field of social network advertising. At the same time, this article also provides a comparative perspective on the practicality of different data augmentation methods, thereby guiding practitioners to choose appropriate techniques to enhance model performance.
Paper Structure (20 sections, 4 figures, 1 table)

This paper contains 20 sections, 4 figures, 1 table.

Table of Contents

  1. Introduction
  2. Methods
  3. Data Collection and Preprocessing
  4. Framework
  5. Synthetic Data Generation
  6. Classification Model Training
  7. Performance Evaluation
  8. Ethical Considerations
  9. Experiments
  10. Model Performance on Original Data
  11. Model Performance on Augmented Data
  12. Comparative Analysis
  13. Interpretation of Results
  14. Implications for Social Network Advertising
  15. Summary of Key Findings
  16. ...and 5 more sections

Figures (4)

  • Figure 1: Data Augmentation Framework. In addition to the regular machine learning train phase and test phase, we add a data augmentation phase at the very beginning to expand the training set by utilizing generative models.
  • Figure 2: GAN with VAE as generator. We embed VAE to our GAN model as generator and regular multi-layer linear network as discriminator.
  • Figure 3: Classification accuracy on test set with the combination of all generative models and all classification models.
  • Figure 4: Result Comparison