商業分析解決方案之規則比較

The Study of Rule Comparison of Business Analytics

陳芃諭(Peng-Yu Chen)

指導教授 ： 黃俊哲

國立暨南國際大學/管理學院/資訊管理學系/碩士(2018年)

摘要

近幾年數據分析與人工智慧一直被廣泛的討論，而這些也一直是企業與政府重點培養、關注的對象。因為它能針對議題，藉由詳細的數據分析得出具有正當性、說服力及可靠的結論，讓決策者能從不同角度判斷，並做出正確的決定。在商業行銷上，這個決定能透過「推薦」提升企業的行銷能力，降低決策錯誤的可能，減少利益損失；而顧客則能購買到期望的產品。
另一方面，節能減碳在近年也時常在各大交鋒會被廣泛的提及，成為被廣泛討論的熱門議題；而讓家庭節能減碳達到目標，更讓府年年討論如何妥善實施政策。因此利用數據分析、規則歸納及規則比較產生規則，給予決策建議，讓各單位的決策者能實施正確的決策，來遏止浪費能源的情形發生，最後達到永續發展的成效，即為本研究的主題。
本研究運用規則歸納法中的約略集合理論，提出一套適用於分析年度顧客資訊的架構，並運用規則比較方法，透過九種行為模式判別顧客規則的趨勢，探討其所需，藉此幫助決策者了解顧客的需求，以便提早修正決策方向，避免失去顧客的信任。

關鍵字

數據分析 ； 規則歸納 ； 能源節約 ； 規則比較 ； 條件屬性 ； 行為模式

並列摘要

In recent years, data analysis and artificial intelligence have been widely discussed, and these have always been the focus of corporate and government training. Because it can be used for the topic, through detailed data analysis to obtain legitimacy, persuasiveness and reliable conclusions, allowing decision makers to judge from different angles and make the right decisions in commercial marketing, this decision can be passed through It is recommended to improve the marketing ability of enterprises, reduce the possibility of decision-making mistakes, and reduce the loss of profits; and customers can purchase the desired products.
On the other hand, energy conservation and carbon reduction have been widely mentioned in major confrontations in recent years, and have become a hot topic that has been widely discussed. Let the family save energy and reduce carbon to achieve the goal, and let the government discuss how to implement the policy properly. Therefore, using data analysis, rule induction and rule comparison to generate rules, give decision-making advice, so that decision makers of all units can implement correct decisions to curb the waste of energy, and finally achieve the effect of sustainable development, that is, the study theme.
This study uses the approximate set theory in the rule induction method to propose a framework suitable for analyzing annual customer information, and uses the rule comparison method to identify the trends of customer rules through nine behavior patterns and explore their needs to help decision-making. People understand the needs of customers in order to correct the decision-making direction early and avoid losing the trust of customers.

並列關鍵字

Data Analytic ； Rule Induction ； Rule Comparison ； Energy Conservation ； Conditional Attribute ； Behavior Pattern

參考文獻

Abrahamse, W., Steg, L., Vlek, C., & Rothengatter, T. (2005). A review of intervention studies aimed at household energy conservation. Journal of environmental psychology, 25(3), 273-291.

Asafuddoula, M., Verma, B., & Zhang, M. (2017, May). An incremental ensemble classifier learning by means of a rule-based accuracy and diversity comparison. In Neural Networks (IJCNN), 2017 International Joint Conference on (pp. 1924-1931).

Bai, C., Dhavale, D., & Sarkis, J. (2016). Complex investment decisions using rough set and fuzzy c-means: an example of investment in green supply chains. European journal of operational research, 248(2), 507-521.

Catlett. J. Megainduction: a test ight. In Proceedings of the Eighth International Workshop on Machine Learning, Ithaca, New York, 1991. Morgan Kaufmann.

Chen, Z. X. A Rough Set Based-Rule Induction for Green Transportation Fleet Selection. Thesis, National Chi-Nan University, 2012