近幾年來，眼鏡連鎖產業呈現飽和狀態，加上經濟不景氣對消費市場帶來負面的嚴重影響，導致消費者幾乎以價格作為唯一的考慮因素。以品牌來說，目前仍以寶島、得恩堂、宏恩、模範、大陸等眼鏡連鎖店位居領導地位，但是單店精品眼鏡，以及隨著量販店興起的眼鏡店，則是新型態的眼鏡業後起之秀。由於科技進步，眼鏡相關商品早已臻成熟階段。而且近年來國內近視的人越來越多，且年齡層亦有逐漸下降的趨勢。 本研究主要是在探討一般消費者對於眼鏡產品的消費習性，以及區分不同消費者對眼鏡產品的消費傾向。進一步以商業智慧的角度觀察眼鏡市場，故蒐集大量商業智慧和眼鏡產品的資料及文獻，然後藉由商業智慧的流程找出眼鏡市場上有價值的資訊。對未來眼鏡業之發展方向提供具體可行之建議。

摘 要 本研究參照Deboeck and Ultsch(1998)想法，不同的是利用多變量分析法中的群集分析來將研究樣本做最合適的分群，再檢視各季各群組是否符合各指標門檻值愈多者，未來投資期間所獲得的報酬也較高，甚至超越類指的現象；另外，也針對年複合成長率以及各指標的門檻值做敏感度分析，而投資期間則分別就短期的1個月、中期的3個月以及長期的6個月做為觀察。實證結果如下： 一、利用CAN SLIM選股策略直接篩選投資標的，本研究的研究樣本中幾乎 沒有一家能夠完全符合；若將條件逐漸放寬只利用C, A, L,三個指標或 C、A二個指標來篩選時，較容易選出投資標的，然而，通過篩選的投資標 的在未來投資期間的平均報酬表現卻未必皆能超越類指表現，顯示若利用 CAN SLIM選股策略的指標來直接篩選未必可以為台灣投資人帶來超越 類指的報酬。 二、利用群集分析法將樣本做最合適的分群後，再與類指報酬表現做比較，顯 示傳統產業中的塑膠業在A=3或A=5下的結果差距不大，顯示此產業有較 穩定的特性，然而實證結果也顯示利用符合指標門檻值的多寡來決定當期 投資的標群組未必能確保選出的標的群組未來投資表現會超越類指。而高 科技產業中的資訊電子業在A=3或A=5下結果明顯不同，以A=3較符合預 期，即符合指標門檻值最多的群組在未來的投資期間表現幾乎皆能超越類 指表現，符合此變化快速的產業特性所需。 三、在對各指標進行敏感度分析中，塑膠業仍未有一個強而有力的結果。而在 資訊電子業中 ，以A=3做為分群資料的情況下，維持原始門檻值依然有較 好的表現。 四、在對投資期間進行敏感度分析中，整體而言，若將投資標的持有3到6個 月，其符合指標門檻值最多的群組平均報酬超越類指的比例較高，也就是 利用CAN SLIM選股策略結合群集分析方法，適合中長期的投資持有。

隨著智慧型終端設備日益普及，使用者對App需求逐漸增加，各大企業也因此開創了一種新的互動性行銷方式。同時，App下載所帶來的龐大商機也促使許多開發人員紛紛加入App的開發行列，造成App的數量呈現爆炸性成長，而讓使用者在面對種類繁多的App時，無法做出有效率的選擇。故本研究將透過文字探勘與kNN集群分析技術，分析網友發表的App推薦文並將App進行分群；再藉由參數的調整，期望能透過衡量指標的評估來獲得最佳品質之分群，以便作為使用者選擇App之參考依據。 為了使大量App進行分群以解決使用者「資訊超載」的問題，本研究以App Store之遊戲類App為分析對象，蒐集了439篇App推薦文章，並依App推薦對象之異同，將其合併成357篇App推薦文章；接著，透過文字探勘技術將文章轉換成可相互比較的向量空間模型，再利用kNN群集分析對其進行分群。同時，藉由參數組合中k值與文件相似度門檻值的調整來獲得最佳品質之分群；其分群品質的評估則透過平均群內相似度等指標來進行衡量；而為了提升分群品質，本研究採用「多階段分群」，以分群後各群集內的文章數量來判斷是否進行再分群或群集合併。 本研究結果顯示第一階段分群在k值為10、文件相似度門檻值為0.025時，能獲得最佳之分群品質。而在後續階段的分群過程中，因群集內文章數減少，故將k值降低並逐漸提高文件相似度門檻值以獲得分群效果。第二階段結束後，可針對已達到分群停止條件之群集進行關鍵詞彙萃取，並可歸類出「棒球/射擊」與「投擲飛行」等6種App類型；其後階段依循相同分群規則可獲得「守城塔防」等14種App類型。分群結束後，共可分出36個群集並獲得20種App類型。分群過程中，平均群內相似度逐漸增加；平均群間相似度則逐漸下降；分群品質衡量指標由第一階段分群後的12.65%提升到第五階段結束時的75.81%。 由本研究可知分群之後相似度高的App會逐漸聚集成群，所獲得之各群集命名結果將能作為使用者選擇App之參考依據；App軟體開發人員也能從各群集之關鍵詞彙中了解使用者所注重的遊戲元素，改善App內容以更符合使用者之需求。而以本研究結果為基礎，透過建立專業詞庫改善分群品質、利用文件摘要技術加強使用者對各群集之了解，或建立App推薦系統等皆可做為未來研究之方向。 / With the popularity of Smart Handheld Devices are increasing, the needs of “App” are spreading. Developers whom devote themselves to this opportunity are also rising, making the total number of Apps growing rapidly. Facing these kind of situation, users couldn’t choose the App they need efficiently. This research uses text mining and kNN Clustering technique analyzing the recommendation reviews of App by netizen then clustering the App recommendation articles; Through the adjustments of parameters, we expect to evaluate the measurement indicators to obtain the best quality cluster to use as a basis for users to select Apps. In order to solve the information overload for the user, we analyzed apps of the “Games” category form App store and sorted out to 357 App recommendation articles to use as our analysis target. Then we used text mining technique to process the articles and uses kNN clustering analysis to sort out the articles. Simultaneously, we fine tuning the measurement indicators to find the optimal cluster. This research uses multi-phase clustering technique to assure the quality of each cluster. We discriminate 36 clusters and 20 categories from the clustering results. During the clustering process, the Mean of Intra-cluster Similarity increases gradually; in the contrary, the Mean of Inter-cluster Similarity reduces. The “Cluster Quality” increases from 12.65% significantly to 75.81%. In conclusion, similar Apps will gradually been clustered by its similarities, and can be used to be a reference by its cluster’s name. The App developers can also understands the game elements which the users pay greater attentions and tailored their contents to match the needs of the users according to the key phrases from each cluster. In further discussion, building specialized terms database of App to improve the quality of the clustering, using summarization technique to robust user understanding of each cluster, or to build up App recommendation system is liking to be further studied via using the results by this research.

本文旨在檢定台電公司現行季節電價月份劃分之合理性，並探討影響用戶別售電量與電費收入之經濟因素。為達成此目的，本文先就負載觀點與成本觀點進行群集分析，以檢定季節電價是否具統計意義之正當性；其次建立經濟計量模型，分別採用戶別之總售電量與總電費收入做為被解釋變數，運用民國88年1月至民國91年12月之月資料進行實證分析。本文建立之經濟模型有二，分別為時間序列以及複迴歸方程式模型。經檢定分析後，本文就各實證參數之經濟意涵加以闡示，最後並提出結論以及未來研究之方向。 本文透過月資料之群集分析，顯示夏月相對於非夏月之群集差異與台電公司現行季節電價夏月與非夏月之月份相一致，證實台電公司季節電價月份劃分之合理性。其次，透過ARIMA時間序列建立之短期電力需求預測模型，經實證結果顯示：電燈與電力用戶別之售電量均逐年增加，預測民國93年1月至民國99年12月，電燈用戶之年售電量平均成長率為3.33%、電力用戶為3.23%。再者，利用複迴歸模型進行實證分析之結果發現：(一)影響售電量之主要變數為溫度。惟因電燈用戶每隔兩月抄表一次，與電力用戶按月抄表之作業方式不同，故電燈用戶每月售電量係受前期(月)溫度影響，而電力用戶則受當期(月)溫度影響。(二)各用戶別之總電費收入與售電量有明顯相關，且經估算出各月售電量之電費收入彈性顯示：電燈用戶約為0.5，電力用戶約為1。由於總電費收入為總售電量與平均電價之乘積，故電燈用戶之電費收入增加1% 時，其售電量僅增加0.5%，顯示總電費的收入增加係有部分來自於平均電價的提高；換言之，就電燈用戶別而言，其電費收入增減變化之百分比除了會受到售電量增減幅度之影響外，亦反映了平均電價變化的情形。同理，對電力用戶來說，其各月售電量之電費收入彈性接近於1，表示電費收入變化1% 時，售電量亦增加1%，即電費收入之增減變化比例主要受到售電量之同向等幅變化所影響。 至於各用戶別之電費收入方面，電燈與電力兩類用戶自民國88年初至91年底四年期間均有逐年增加之趨勢，惟電力用戶之年增加幅度有隨時間遞減之現象，且歷年大抵以7-10月份較高，2月份最低。此外，影響用戶別電費收入之解釋變數中，各類用戶之售電量最為顯著，其參數值係隱示每增加一度售電量對其電費收入之影響。其中，電燈用戶之估計參數值為2.69，而電力用戶則為1.35。再者，由其電費收入之售電量彈性係數可以發現：電燈用戶約為1.2，電力用戶約為0.7，顯示電燈用戶總售電量增加1%時，總電費收入增加的幅度大於1%，而電力用戶則相反。推估電力用戶此一彈性係數較電燈用戶低之原因在於：電力用戶與電燈用戶之電價結構不同，前者係採需量電費與能量電費之兩部電價制，而後者僅包含流動電費之一部電價。最後，實證結果亦顯示電力系統之尖峰負載與負載率會影響電費收入，惟其影響幅度不大。 / A Study on Customer-by-Category Energy Sales and Power Sales Revenue Model: The Case of Taiwan Power Company Abstract The main purposes of this study are to examine the rationality of the seasonal pricing scheme defined by summer and non-summer months and to identify economic factors influencing customer-by-category energy sales and power sales revenue, utilizing the data of Taiwan Power Company (Taipower) as an empirical case. In order to achieve this objective, the cluster analysis from the perspective of load pattern and cost pattern are examined respectively to see if the seasonal pricing scheme has statistical meaning in its pattern differences in terms of summer vs. non-summer season. Second, two economic models including time-series analysis and multiple regression equations are formulated for the empirical case study. The subtotal energy sales and the subtotal power sales revenue by different type of customer categories, i.e. lighting and industrial customers, are set to be the explained variables. Data from January 1999 to December 2002 are collected for modeling simulation tests. The economic meanings and policy implications of the modeling results are elaborated on. And conclusions with directions for further research are presented. Through the cluster analysis utilizing monthly data within the time frame mentioned above, empirical research results on the grouping cluster of summer vs. non-summer months shows a consistent trend with those defined by Taipower’s present seasonal pricing scheme. Second, the empirical results of ARIMA time-series model show that the forecasted energy sales of both lighting and industrial customers will be gradually increasing through January 2004 to December 2010, and the average annual growth rate of energy sales for the lighting customer is 3.33%, and for the industrial customer is 3.23%. On the other hand, the empirical research results through the multiple regression equations show that the main factor affecting the energy sales is temperature. Due to the different time schedules for reading electricity meters between the lighting customer and the industrial customer, i.e. the time interval for reading the meter of lighting customers is every two months and for industrial customers is every month, the monthly energy sales of the lighting customer are directly related to the temperature of the previous month, while the monthly sales of the industrial customer are directly related to the temperature of the present month. In addition, for each type of customers, there is an obvious correlation between the total power sales revenue and the total energy sales. Furthermore, the estimated elasticity of the total power sales revenue versus total energy sales is about 0.5 for the lighting customer, and about 1 for the industrial customer. Since the total power sales revenue is the product of total energy sales times the average electricity price, when the total power sales revenue increases 1% with the total energy sales only increases 0.5%, it implies that the increase of total power sales revenue not just only comes from the increase of energy sales, but also partially affected by the increase of average electricity price. Similarly, for the industrial customer, when the elasticity of their monthly total power sales revenue versus total energy sales is close to 1, it implies that when the total power sales revenue increases 1%, the total energy sales also increase about 1%. In other words, the change of percentage of the total power sales revenue is mostly attributed to the variation of total energy sales, not because of the average electricity price. As for the simulation results of the total power sales revenue, those of the lighting and industrial customers are both gradually increasing between the years 1999 to 2002. However, the increasing pace of the industrial customer tended to slow down. Moreover, both types of the customers possess a similar trend that their total power sales are higher in statistical meaning for the months from July to October, and lower for February, for those above three years. Besides, among the variables affecting each type of customer’s power sales revenue, the energy sales is the most significant one, its parameter implies that whenever the total energy sales increases one unit, i.e. one kwh, it would affect the total power sales revenue by that amount equivalent to the figure of the parameter. According to the empirical results, the estimated parameter mentioned-above of the lighting customer is 2.69, and 1.35 of the industrial customer respectively. That implies one kwh unit price for the lighting customer is 2.69 N.T. dollars, and 1.35 N.T. dollars for the industrial customer. Moreover, from the elasticity of the total energy sales versus the total power sales revenue, it shows that the elasticity of the lighting customer is around 1.2, and the elasticity of the industrial customer is around 0.7. The underlining reason of the difference between the two figures could be that the electricity pricing structure of the lighting and industrial customers are quite different. The industrial customer is charged by two-part tariff including a demand charge for the capacity use and an energy charge for the kwh use. While the lighting customer is charged simply by a single rate, i.e. the energy use. Finally, the empirical results also show that the magnitude of the peak load and the load factor of the whole electricity system also affect the total power sales revenue of each type of the customer, though with much less effect.

在網際網路快速發展下，大量使用者在獲取知識與新聞的管道，已由傳統媒體轉移到網路上。網路活動下使用者互動後所留下的訊息，也就是網路口碑，也逐漸受到重視。而隨著經濟發展，國人在固定薪資下無法負擔高房價、高物價的生活，如何透過投資理財來增加自身財富，已是非常普遍，其中又以股市投資為大眾所重視之途徑。 網路新聞的發布，除了具有網路的即時性外，配合使用者閱讀內化後所留下的評論，應含有比網路新聞本身內容更多的資訊，投資者便可藉此找尋隱含之中大量市場消息與資訊。 本研究為了在龐大的資料量中，幫助使用者挖掘其背後之涵義，進而提供投資預測，將蒐集網路新聞及其閱讀者評論共1068篇，並分為訓練資料與測試資料，使用文字探勘及相關技術做前處理，再透過kNN分群技術，計算訓練資料文件間相似度，將大量未知資料依其相似度做分群後，利用歷史股價訊息對群集結果之特徵分析解釋之並建立預測模型，最後透過測試資料將模型分群結果進行評估，進而對股價趨勢做出預測。 / With the rapid development of the Internet, the way of user access to knowledge and news transfer from traditional media to the network. Internet word-of-mouth, the message generated from users' interaction on internet, attracts more and more people's attention. With economic development, people in the fixed salary cannot afford high prices and high price in live. People increase their own wealth through investment is very common, among which the stock market is the way to public attention. Internet news has the immediacy of the Internet. And the comments left with the user to read the internalization should contain more information than the Internet news. Investors can find the market news and information by Internet news and comments. In this study, in order to help the user to find the meaning behind the huge amount of data, and thus provide investment forecast. We will collect 1068 of internet news and reader reviews to divide into training data and test data using text mining and related technologies to do the pre-treatment, and then calculate the similarity between the training data by kNN, a lot of unknown data according to their similarity clustering. Cluster through the historical share price analysis and modeling. Finally, the model clustering results were evaluated through the test data to predict price trends. The prediction model from training data clustering, use test data to do the evaluation found: k = 15, the similarity threshold value = 0.05, cluster the results of the F-measure performance up to 56% rise in the cluster. K values and the similarity threshold will be adjusted to obtain the most favorable results of the model