芒果是臺灣前五大經濟水果，近年來由於消費者健康意識抬頭，以天然原味在地生產為訴求的玉井芒果乾成為很受歡迎的臺灣味伴手禮。也隨著網路購物平台的興起，配合網站的人性化視覺及文案設計，與日趨便利的物流服務如：宅配業者的宅配到府、指定時間服務、到店取貨、貨到付款等物流及金流的創新，消費者能透過即時方便的購物平台，迅速購買芒果乾等傳統農產品。然生產芒果乾業者多屬於微小型農企業，網路行銷資源相對薄弱。本研究將透過建立商業智慧模型以深入了解農產加工品購物網站之客戶購買行為，分析農產公司網站訂購歷史資訊數據，以建立該農產公司消費者之購物型態，以做為輔助未來行銷策略活動之制訂，以達精確行銷之效。
商業智慧方法(Business Intelligence, BI)是將原始資料如何轉變成對企業有用的資訊跟智慧的一個活動流程，透過分析(Analysis)、洞悉(Insight)、行動(Action)、衡量(Measurement)等四個不斷循環的商業智慧流程萃取海量資料中的有效資訊，並透過建立線上分析處理(Online Analytical Processing, OLAP)的資料結構及模型架構了解該農產公司消費者之購物型態與行銷策略之關係與因數，建立指導性和預測性分析做為行銷策略的方針。
本研究透過商業智慧雛形系統之建置，彙整蜜旺果公司2014至2017年商務網站瀏覽及交易之海量歷史交易資紀錄，依據研究主題相關需求，提供即時且完整的人性化視覺分析，以洞悉個案公司商務網站之整體消費行為面貌並協助找出目標客群，並了解目前台灣芒果乾業者等微農企業的社會功能與可能面臨的危機，提供業者更妥適、精確的行銷參考策略。並做未來之經營業績預測，以輔助相關決策人員做出更妥適有效益之行銷策略，使之在芒果乾產業中保有競爭經營優勢。

Mango is the one of the top five economic fruits in Taiwan. Due to rising consumer health awareness in recent years, Yujing dried mangoes, which are naturally produced in the local area, have become a popular Taiwanese gift and souvenir. With the rise of online shopping based on user-friendly visual and textual design of the website, and the increasingly convenient logistics services such as home delivery and designated time services, now consumers can quickly purchase traditional products such as dried mangoes through instant and convenient shopping platforms. However, dried mangoes are mostly produced by micro-agricultural enterprises, and their network marketing resources are relatively weak. This study will establish a business intelligence model to gain insights into the customer purchase behavior at the shopping website of agricultural products. Moreover, we shall analyze the agricultural company's website ordering information to establish a shopping model for precision sales and marketing strategies.
Business Intelligence (BI) aims at transforming raw data into information and intelligence that are useful to the enterprise. Through the processes of analysis, insight, action, and measurement, BI can extract effective information from massive data, and help people understand the relationship between the shopping model of the agricultural company and the marketing strategy by establishing an online analytical processing (OLAP) data structure and model architecture for predictive analysis.
Through the establishment of a BI prototype system, this study captures massive data of browsing and transactions from Miwango Company's website from 2014 to 2017, providing immediate and complete visual analysis and feedbacks based on relevant topics for business needs. The analysis of overall consumer behavior helps to identify target customers and understand the social functions and potential crises of micro-agricultural enterprises such as Taiwan's dried mangoes, providing a more appropriate guidelines for decision-makers to make more effective marketing strategy for precision sales. Such a system can effectively help the company to maintain a competitive business advantage in the dried mango industry.

中文文獻
2010，揪團熱門芒果乾試吃香Q是關鍵，自由時報週日特別企劃。
尹相志，2009，SQL Server 2008 OLAP多維度分析，台北市：悅知文化。
王必昌，1961，重修台灣縣志，台灣文獻叢刊，第 113 種，台北市：台灣銀行經濟研究室。
史進旺，2012，綠色健康食品 台南芒果乾評鑒第一名，新唐人。
吳淑玲，2015，真空乾燥再進化果乾留住原味；聯合新聞。
林宏聰，2015，高雄水果前進杜拜果乾最夯；中時電子報。
林欣榜，2010，蔬果加工理論與實務，新北市；全民圖書。
莊老達，2013，台灣芒果產業現況與輔導措施，農委會；提升台灣芒果產業價值鏈研討會專刊。
陳豪傑，2016，大數據玩行銷 ，台北市；30雜誌。
陳曉菁，王仕賢，2013，芒果多元化利用，農委會；提升台灣芒果產業價值鏈研討會專刊。
曾光華，2014，行銷管理：理論解析與實務應用，新北市；前程文化。
黃文記，2015，百貨設攤 當禮品 芒果乾變時尚；中華日報。
黃旭愉，2005，決策分析的利器—線上分析處理(OLAP)；華南銀行資訊室。
黃秋香、簡相堂，2015，特色食品之價值開發與國際化策略，新竹市；財團法人食品工業發展研究所。
劉文良，2007，電子商務：雲端時代：基峰資訊。
劉婉君，2016，臺灣農產品電子商務發展現況及施政展望，農委會。
英文文獻
Biere, M. (2003). Business Intelligence for the Enterprise: Prentice Hall Professional.
Bresfelean, V. P., Bresfelean, M., Ghisoiu, N., & Comes, C. A. (2007). Data Mining Clustering Techniques in Academia. Paper presented at the 9th International Conference on Enterprise Information Systems, Funchal, Madeira - Portugal.
Chaudhuri, S., Dayal, U., & Narasayya, V. (2011). An overview of business intelligence technology. Communications of the ACM, 54(8), 88-98.
Codd, E. F., Codd, S. B., & Salley, C. T. (1993). Providing OLAP (on-line analytical processing) to user-analysts: An IT mandate (Vol. 32): Codd and Date.
Davenport, T. H. (2013). Analytics 3.0. Harvard Business Review, 91(12), 64-72.
Palaniappan, S., & Ling, C. (2008). Clinical decision support using OLAP with data mining. International Journal of Computer Science and Network Security, 8(9), 290-296.
Pourabbas, E., & Rafanelli, M. (2000). Hierarchies and relative operators in the OLAP environment. ACM Sigmod Record, 29(1), 32-37.
Rouibah, K., & Ould-ali, S. (2002). PUZZLE: a concept and prototype for linking business intelligence to business strategy. Journal of Strategic Information Systems, 11(2), 133-152.
Sell, D., Cabral, L., Motta, E., Domingue, J., & Pacheco, R. (2005). Adding semantics to business intelligence. Paper presented at the Database and Expert Systems Applications: 16th International Conference, Copenhagen, Denmark.
Thomas Jr, J. H. (2001). Business intelligence–Why? eAI Journal, 47-49.
Vitt, E., Misner, S., & Luckevich, M. (2002). Business Intelligence: Making Better Decisions Faster: Microsoft Press.