• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 2007.11a
• /
• pp.425-434
• /
• 2007

The sponsored search has become significant channel of online advertising, and the large sized advertisers have appeared, so the sponsored search strategy is becoming more important. Since CPC(Cost-per-Click) advertising has different price according to keyword, it is difficult to manage the a lot of keywords at one time. So, the purpose of this study is to investigate the factors which influence on the cost-per-click of sponsored search advertising. That is, there are four factors: impression, CTR(Click through Rate), conversion rate, and keyword's length. for the regression analysis, we use the actual data which is gotten from an ad agency. The result of that, the impression and keyword's length influence cost-per-click positively. However, CTR & conversion rate have no influence on it unexpectedly.

• International Journal of Knowledge Content Development & Technology
• /
• v.1 no.1
• /
• pp.7-24
• /
• 2011

This study aims to measure the impact of these two variables on consumers' 'click-through' rates (the number of users that click on the ad compared to the number of times the ad is delivered). The result is as follows. First, search ads play a critical role in drawing consumers to advertisers' websites. Once search ads are placed, the number of visitors increased tenfold. Secondly, when search ads are keyed to highly-involved words such as 'IDC', 'hosting' and 'co-location', click-through rates significantly fluctuate according to the type of advertising message. In this case, consumers respond much more positively to ads highlighting credibility and product quality than to ads with emphasis on sales and events. Thirdly, the placement of search ads also matters. The ad placed first in the search list overpowers ads in the third or fifth place in terms of click-through rates. However, there was no significant difference of click-through rates between ads in the third place and ads in fifth. Lastly, when estimating which variable plays the bigger role in bringing traffic to advertisers' websites, consumers are more receptive to the substance of the advertising message than to its placement, under the circumstances of high involvement.

• Journal of Information Technology Services
• /
• v.11 no.3
• /
• pp.257-267
• /
• 2012

Many advertisers utilize sponsored search in search engines since customers want to find relevant information on their purchases from the search engines. Many factors have influences on price per click of the sponsored search. These influences are different based on the types of keywords such as search/experience or prominent/specific. However, differences of the influences have not been studied well. Thus, this study wants to identify the differences of the influences according the type of keywords. One month data of keyword advertising were collected from Naver. The influences of search number, click through rate, and competition on price per click were different according to the keyword types.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.522-523
• /
• 2023

CTR(Click Through Rate) 예측은 사용자가 광고나 아이템을 클릭할 확률을 예측하는 데 사용되는 용어로, 광고 분야에서 중요한 연구 분야로 자리 잡았다. 인터넷 데이터의 양이 증가함에 따라, 전통적인 피쳐 엔지니어링의 인건비는 계속해서 상승하고 있다. 특징 상호 작용에 대한 의존도를 줄이기 위해, 본 논문은 TMH(Two-Tower Multi-Headed Attention Neural Network) 접근법이라고 하는 명시적인 특징 상호 작용과 암시적인 특징 상호 작용을 결합한 융합 모델을 제안한다. CTR 예측에서 TMH 의 효과를 평가하기 위해 3 개의 실제 데이터 세트를 사용하여 많은 수의 실험을 수행하였다. 성능은 3 개의 데이터 세트에서 0.12%, 0.41% 및 0.68%으로 향상되었다.

• Journal of Information Processing Systems
• /
• v.17 no.2
• /
• pp.369-384
• /
• 2021

In a personalized product recommendation system, when the amount of log data is large or sparse, the accuracy of model recommendation will be greatly affected. To solve this problem, a personalized product recommendation method using deep factorization machine (DeepFM) to analyze user behavior is proposed. Firstly, the K-means clustering algorithm is used to cluster the original log data from the perspective of similarity to reduce the data dimension. Then, through the DeepFM parameter sharing strategy, the relationship between low- and high-order feature combinations is learned from log data, and the click rate prediction model is constructed. Finally, based on the predicted click-through rate, products are recommended to users in sequence and fed back. The area under the curve (AUC) and Logloss of the proposed method are 0.8834 and 0.0253, respectively, on the Criteo dataset, and 0.7836 and 0.0348 on the KDD2012 Cup dataset, respectively. Compared with other newer recommendation methods, the proposed method can achieve better recommendation effect.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.11 no.4
• /
• pp.1468-1474
• /
• 2010

The establishment of a successful business must be preceded by comprehensive entrepreneurial preparation and research, as well as the development of a truly attractive business idea. Research to-date has tended to be based solely on factors relating to entrepreneurial activity or business performance. Research into the development and evaluation of a business idea has been insufficient. The purpose of this research is to propose a methodology for evaluating the attractiveness of a business idea objectively. This research measures the attractiveness of a business idea by the click through rate (CTR) to a website generated by specific keyword entry into internet search engines. The attractiveness of a business idea can be presented by the formula: number of relevant keyword searches x CTR on search results. As the number of searches for individual keywords is published by the search engines and it is possible to estimate CTRs for specific search results, we can objectively evaluate the attractiveness of a business idea. By analyzing keyword search data and CTRs obtained from search engines over a one month period, 1124 keywords that relate to foreign language education have been identified. A regression formula has also been derived, predicting the click through rate for search results. This research and its findings can be used to raise the success rates of new businesses; proposing objective guidelines for business idea development and evaluation. It is particularly meaningful because it introduces a new methodology to the arena.

• Knowledge Management Research
• /
• v.22 no.4
• /
• pp.27-40
• /
• 2021

Click-Through Rate (CTR) prediction is a key function that determines the ranking of candidate items in the recommendation system and recommends high-ranking items to reduce customer information overload and achieve profit maximization through sales promotion. The fields of natural language processing and image classification are achieving remarkable growth through the use of deep neural networks. Recently, a transformer model based on an attention mechanism, differentiated from the mainstream models in the fields of natural language processing and image classification, has been proposed to achieve state-of-the-art in this field. In this study, we present a method for improving the performance of a transformer model for CTR prediction. In order to analyze the effect of discrete and categorical CTR data characteristics different from natural language and image data on performance, experiments on embedding regularization and transformer normalization are performed. According to the experimental results, it was confirmed that the prediction performance of the transformer was significantly improved when the L2 generalization was applied in the embedding process for CTR data input processing and when batch normalization was applied instead of layer normalization, which is the default regularization method, to the transformer model.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2001.11a
• /
• pp.389-392
• /
• 2001

본 논문에서는 웹 데이터 마이닝을 통하여 웹 사이트를 방문한 사용자의 컨텐츠 유형에 따른 정보를 조사하고, 필터링 과정을 통해 분류화하고, 이러한 과정을 통해 얻은 정보를 이용하여 뉴스레터를 발송하며, 발송된 뉴스레터로부터의 컨텐츠 유형에 따른 CTR(Click Through Rate)과 사용자 반응을 추적하여 이러한 정보를 분석하고 사용자 프로파일 및 웹 사이트로부터 분류화된 정보, 그리고 추적된 정보와 함께 뉴스레터 컨텐츠를 재구성하는 개인화된 자동화 뉴스레터 시스템을 설계하고 구현한다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.10
• /
• pp.4833-4848
• /
• 2019

This paper introduces the structure and effects of Kakao's news curation algorithm, which is created based on the Deep Reading Index (DRI). The DRI examines the extent of deep reading through content reading time, that is, the duration of reader engagement with an article. Current news curation algorithms focus on reader choice, with the click-through rate or pageviews as the gauge for consumption frequency. DRI is a product of the challenge of introducing and adopting a new factor called 'consumption time' instead of 'frequency of consumption', which is the basis of existing curation algorithms. The analysis of DRI-based services proves that the new algorithm can act as a curation system that is more effective in providing in-depth and quality news reports.

• Journal of Service Research and Studies
• /
• v.14 no.2
• /
• pp.1-17
• /
• 2024

One of the most important decisions for managers in the online banner advertising industry, is to choose the best banner alternative for exposure to customers. Since it is difficult to know the click probability of each banner alternative in advance, managers must experiment with multiple alternatives, estimate the click probability of each alternative based on customer clicks, and find the optimal alternative. In this reinforcement learning process, the main decision problem is to find the optimal balance between the level of exploitation strategy that utilizes the accumulated estimated click probability information and exploration strategy that tries new alternatives to find potentially better options. In this study we analyze the impact of word-of-mouth effects and the number of alternatives on the optimal exploration-exploitation strategies. More specifically, we focus on the word-of-mouth effect, where the click-through rate of the banner increases as customers promote the related product to those around them after clicking the exposed banner, and add it to the overall reinforcement learning process. We analyze our problem by employing the Multi-Armed Bandit model, and the analysis results show that the larger the word-of-mouth effect and the fewer the number of banner alternatives, the higher the optimal exploration level of advertising reinforcement learning. We find that as the probability of customers clicking on the banner increases due to the word-of-mouth effect, the value of the previously accumulated estimated click-through rate knowledge decreases, and therefore the value of exploring new alternatives increases. Additionally, when the number of advertising alternatives is small, a larger increase in the optimal exploration level was observed as the magnitude of the word-of-mouth effect increased. This study provides meaningful academic and managerial implications at a time when online word-of-mouth and its impact on society and business is becoming more important.