Keyword Advertising Cost Prediction Using Crawling and Machine Learning Techniques 


Vol. 14,  No. 4, pp. 248-256, Apr.  2025
https://doi.org/10.3745/TKIPS.2025.14.4.248


PDF
  Abstract

Due to the recent rapid growth of online advertising, analysis and prediction of advertising costs are becoming essential elements in establishing a company's marketing strategy. Advertising costs are one of the core marketing costs that companies spend to promote their products or services, and their importance is becoming more prominent in order to maximize the efficiency of advertising campaigns and to gain an edge in the bidding competition between advertisers. This study proposes a machine learning-based regression model that predicts keywords used in various domains and advertising costs for those keywords. The data used in this study include keyword data collected using crawling technology, advertising cost prediction data extracted through Naver API(Application Programming Interface), and advertising agency data. Through this, we tried to develop a model that can effectively predict the advertising cost of each keyword. In the research process, a regression model based on the LightGBM(Light Gradient Boosting Machine) was constructed, and the MAE(Mean Absolute Error) was used as a performance evaluation index. Finally, an excellent prediction performance of less than 250 MAE was achieved. Therefore, it is expected that marketers will be able to use the data presented in this study to support efficient decision-making between advertisers and advertising agencies.

  Statistics
  Cite this article

[IEEE Style]

K. Jeon, J. Lim, S. Kim, H. Cho, D. Jung, J. Kim, Y. Song, K. Kim, "Keyword Advertising Cost Prediction Using Crawling and Machine Learning Techniques," The Transactions of the Korea Information Processing Society, vol. 14, no. 4, pp. 248-256, 2025. DOI: https://doi.org/10.3745/TKIPS.2025.14.4.248.

[ACM Style]

Kyungmin Jeon, Jaeyoung Lim, Sunghyun Kim, Hyunseo Cho, Daesik Jung, Jongwon Kim, Younggi Song, and Kyungsoo Kim. 2025. Keyword Advertising Cost Prediction Using Crawling and Machine Learning Techniques. The Transactions of the Korea Information Processing Society, 14, 4, (2025), 248-256. DOI: https://doi.org/10.3745/TKIPS.2025.14.4.248.

Forms

Search
(IN TITLE, AUTHOR, ABSTRACT,KEYWORDS)

Advanced Search ▼

POPULAR KEYWORDS
(TOP 10 KEYWORDS)

Recent Publications
(LAST 3 YEARS)

Old Journals

Indexing

All publications of TKIPS is indexed in DOI, EBSCO, Google Scholar, Crossref, and CrossCheck.

TKIPS is also selected as the Journal for Accreditation by NRF (National Research Foundation of Korea).

Related Journals