Advertising Optimization and Feature Analysis Based on Machine Learning

Yao Li

2024

Abstract

Under the impact of the pandemic for three years, the market economy has shown an overall downward trend, and the consumption level of the public has decreased. Maintaining product sales and stimulating consumer desire have become the main problem for the industry. By using machine learning algorithms to optimize advertisements, industry costs can be reduced and better sales can be achieved. This study first associates the objectives with features to facilitate relevant practitioners to carry out corresponding optimizations. Secondly, prioritizing the importance of data features is beneficial for relevant practitioners to have a bias towards their work and facilitate subsequent model building. Finally, based on the importance of the corresponding features, select the features with higher importance to establish a click-through rate prediction model for advertising rating. The random forest model can achieve an accuracy of 95% in predicting advertising click-through rates. Then the experimental results show that using machine learning methods to construct a model can predict the subsequent click-through rate of advertisements to optimize them. By predicting and rating existing advertisements and observing the expected results, it is convenient for relevant advertising design and placement personnel to make improvements, to achieve optimal efficiency in advertising.

Paper Citation

in Harvard Style

Li Y. (2024). Advertising Optimization and Feature Analysis Based on Machine Learning. In Proceedings of the 1st International Conference on Data Science and Engineering - Volume 1: ICDSE; ISBN 978-989-758-690-3, SciTePress, pages 70-76. DOI: 10.5220/0012822000004547

in Bibtex Style

@conference{icdse24,
author={Yao Li},
title={Advertising Optimization and Feature Analysis Based on Machine Learning},
booktitle={Proceedings of the 1st International Conference on Data Science and Engineering - Volume 1: ICDSE},
year={2024},
pages={70-76},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012822000004547},
isbn={978-989-758-690-3},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 1st International Conference on Data Science and Engineering - Volume 1: ICDSE
TI - Advertising Optimization and Feature Analysis Based on Machine Learning
SN - 978-989-758-690-3
AU - Li Y.
PY - 2024
SP - 70
EP - 76
DO - 10.5220/0012822000004547
PB - SciTePress