辨識行動廣告重要因素之研究

A Study of Identifying the Crucial Factors of Mobile Advertising

劉俊誠(CHUN-CHENG LIU)

指導教授 ： 陳隆昇

朝陽科技大學/資訊學院/資訊管理系/碩士(2016年)

摘要

行動廣告(Mobile advertising)隨著行動應用程式(Applications)和行動網站的快速發展而興起，行動廣告的市場規模也急遽成長。行動廣告雖然可以在任何時間地點將廣告內容依據個人需要，透過行動裝置傳達給顧客，但對廣告主而言，如何提升行動廣告是一項重大的議題。因此，本研究主要目的在於找出影響行動廣告三大績效 (點閱率、客戶忠誠度、客戶再購率)的重要因素，進而提供廣告商在設計行動廣告有用的資訊。本研究試圖定義行動廣告因素，並利用支持向量機遞迴式特徵消除(Support vector machine recursive feature elimination, SVM-RFE)、Relief-F、線性迴歸(Linear Regression)、決策樹(Decision trees)、基於一致性方法(Consistency-based approach)、基於關聯性方法(Correlation-based approach)等六種特徵選取方法，進而辨識出對提升三項依變數有影響的行動廣告重要因素，希望對行動廣告的企業能夠改善行動廣告的價值，促進行動廣告市場能蓬勃發展。

關鍵字

基於關聯性方法 ； 基於一致性方法 ； Relief-F ； SVM-RFE ； 特徵選取 ； 行動廣告 ； 決策樹 ； 線性迴歸

並列摘要

With the rapid development of applications (APP) and population of mobile devices, the market share of mobile advertisements grows dramatically. Mobile advertisements can reach potential customers at any time and place based on individual needs, but for advertisers, how to enhance the influence of click through rate (CTR), customer loyalty and customer repurchase rate has become one of major issues. Therefore, this study aims to identify the important factors of influencing these three independent variables of mobile advertisements, included click trough rate, customer loyalty and customer repurchase rate, thus to provide advertisers useful information for the design of mobile advertisements. This work attempts to define the potential factors of mobile advertising, and then employ support vector machine recursive feature elimination (SVM-RFE), Relief-F, Linear Regression, Consistency-based, Correlation-based and Decision Trees (DT) feature selection methods to identify the key attributes to enhance these three independent variables. Findings can be used to improve the benefits of mobile advertising and to increase the market share of mobile advertisements.

並列關鍵字

Correlation-based approach ； Consistency-based approach ； Relief-F ； SVM-RFE ； Feature selection ； Mobile advertising ； Decision tree ； Linear Regression

參考文獻

[1] Alicia, I. Y., Cristina, O. P. and Eva, R. L., “Attitudes toward mobile advertising among users versus non-users of the mobile Internet,” Telematics and Informatics,” Vol. 32, pp. 355–366, 2015.

[2] Aytuğ, O., “A fuzzy-rough nearest neighbor classifier combined with consistency-based subset evaluation and instance selection for automated diagnosis of breast cancer,” Expert Systems with Applications, Vol. 42, pp. 6844–6852, 2015.

[3] Almuallim, H. and Dietterich, T. G., “Learning with many irrelevant features,” Proceedings of the Ninth National Conference on Artificial Intelligence, pp.547-552, 1991.

[4] Alireza, M., Heshaam, F., “Using decision tree to hybrid morphology generation of Persian verb for English–Persian translation,” Computer Speech & Language, Vol. 32, Issue 1, pp. 145-159, July 2015.

[5] Bristol, T. J., “Nursing school? There's an app for that!,” Teaching and Learning in Nursing, Vol. 9, pp. 203–206, 2014.