Categorizing Online Advertisements with Machine Learning Models: Categorizing Online Advertisements with Machine Learning Models

Mohammad Taghi Taghavifard; Pegah  Farazmand; Khatereh Farazmand; Saeedreza  Jadidi

Authors

Mohammad Taghi Taghavifard Department of Management, Faculty of Management and Accounting, Allameh Tabataba’i University, Tehran, Iran Author
Pegah Farazmand Department of Management, Faculty of Management and Accounting, Allameh Tabataba’i University, Tehran, Iran Author
Khatereh Farazmand Department of Health, Faculty of Health, Shahid Beheshti University of Medical Sciences, Tehran, Iran Author
Saeedreza Jadidi Department of Mechanical, Industrial and Aerospace Engineering, Concordia University, Montreal, QC, H3G 1M8, Canada Author

Keywords:

Machine Learning Models,, Advertising Segmentation,, Target Audience,, Online Ads.

Abstract

Advertising segmentation, also known as audience or market segmentation, constitutes a critical facet of marketing. It involves subdividing a large target population into more manageable groups or segments. By employing advertising grouping, businesses can tailor content and keywords to each group of advertisements, thereby enhancing the effectiveness of their marketing efforts. This project explores two machine learning models for advertising grouping, achieving an impressive efficiency rate of over 90%. The study encompasses a dataset of 2000 online advertisements divided into five advertising groups, with 1600 data points used for training and 400 for testing. The results indicate that the Support Vector Classifier (SVC) and Linear Regression (LR) models perform well in the categorization of advertisements.

Categorizing Online Advertisements with Machine Learning Models