跳到主要內容

臺灣博碩士論文加值系統

(44.192.247.184) 您好!臺灣時間:2023/01/30 13:45
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::

詳目顯示

: 
twitterline
研究生:張悅頎
研究生(外文):Yueh-Chi Chang
論文名稱:運用遺傳演算法來檢測共同移動股票之關鍵決定因子
論文名稱(外文):Using Genetic Algorithms to probe significant factors leading to correlated movement of stocks
指導教授:白小明
口試委員:邱昭彰徐苑玲陳煒朋
口試日期:2012-3-31
學位類別:碩士
校院名稱:元智大學
系所名稱:光電工程學系
學門:工程學門
學類:電資工程學類
論文種類:學術論文
畢業學年度:100
語文別:中文
論文頁數:50
中文關鍵詞:名稱類似共同移動資料探勘遺傳演算法
外文關鍵詞:Similar NameCo-movementData MiningGenetic Algorithm
相關次數:
  • 被引用被引用:0
  • 點閱點閱:248
  • 評分評分:
  • 下載下載:7
  • 收藏至我的研究室書目清單書目收藏:1
本研究檢測名稱類似的股票,是否常常使得投資人產生混淆,而導致不理性的投資行為,進而影響股價的移動。在台灣這個使用中文系統的新興市場,是否較歐美成熟市場更為顯著且普遍存在。本研究以股票報酬的相關係數值來評估價格移動的共同程度,當配對股票間的係數值大於其個別股票對其自身產業的係數值時,表示存在共同移動現象。研究結果發現,不管是用傳統或是用移動平均法來計算相關係數,都沒有呈現股票報酬連動的行為。進一步根據特別高或特別低的日報酬篩選出報酬觸發事件,研究分析發現名稱類似的配對股票的相關係數均高於其與自身產業的相關,表示不理性的投資行為在有資訊發生的特殊事件如好消息或壞消息下才會發生,而非存在於平日一般的交易中。
再者,本研究探討此連動關係的關鍵影響因子,研究發現名稱型態與股票特性會影響連動關係。兩配對股票名稱中有兩個字相同,或是第一字相同、第二字發音相同,其共同移動的可能性就大為提高。此外,這種連動關係是單方向的,觸發股有較跟隨股為大的市值、成交值及周轉率,顯示股票特性中公司規模及交易流動性也是影響名稱類似股票是否會共同移動之關鍵因子。最後,採用資料探勘技術建立並評估相關配對辨認模型。實驗結果顯示GAKP對於連動配對股票的分類正確率是最高的。成交值的比值及股票名稱編碼在模型中的權重最高,顯示對分類之影響最大,高成交值的股票會帶動成交值較低的股票價格,配對股票編碼的型態有助於判別出有共同移動的名稱類似股票。
This study examined correlation of stocks which names are similar. Investors may be confused by the stock names so that make irrational investment behavior. In the emerging market of Taiwan, Chinese characters are used for ticker symbol, this study probes co-movement phenomenon. The results show that there was no co-movement despite of general or moving average correlation. This study also analyzes special return instance (+/-3%) in the price of one equity triggered a corresponding change in its partner, and finds some pairs are co-moved. It represents co-movement phenomenon only happens on information occurs.
Furthermore, this study analyzes the key factor of co-movement to discover the relationship between similar name types and stock features. If stocks in a pair has 2 same characters, or 1 same character another has same pronounce, the possibility of co-movement raises. Besides, co-movement is only 1-way direction, the capitalization, volume and turnover of trigger stock are greater than follower. It means the size of corporate and the trade flows are also key factors of co-movement. Finally, this study constructs data mining evaluation model to identify correlated and non-correlated pairs. The result shows GAKP classification gets best recall in correlated pairs. The ratio of volume and the code of similar name are the most 2 important weight of optimized model. It means high volume stocks will lead small volume stock in a pair, and similar name type can help to distinguish the co-movement of similar name stocks.
書名頁 i
中文摘要 iv
英文摘要 v
壹、 緒論 1
1.1研究背景與動機 1
1.2研究目的與結果 2
貳、 文獻探討 4
2.1公司名稱變更 (Corporate Name Change) 4
2.2股票名稱類似 (Similar Stock Name) 5
2.3資料探勘 (Data Mining) 6
參、 資料與研究方法 8
3.1研究架構 8
3.2資料來源 10
3.3樣本選取 (Sample Selection) 10
3.3.1選取名稱類似股票的步驟及準則 (Selection Steps and Criteria) 10
3.3.2 樣本描述 (Sample Description) 11
3.4配對股票之編碼 (Coding the Paired Stocks) 13
3.5共同移動之衡量 (Comovement Measure) 13
3.5.1配對股票之相關係數 (Correlation Coefficients of Paired Stocks) 13
3.5.2相關係數之移動平均法 14
3.5.3觸發事件之關係數(Correlation Coefficients of Return Triggering Events) 15
3.6資料探勘及建立預測模型步驟 17
肆、 研究結果 21
4.1敘述性統計 21
4.2相關係數分析 (Correlation Analysis) 22
4.2.1配對股票之相關係數 (Correlations) 22
4.2.2配對股票移動平均之相關係數 (Moving Average Correlations) 25
4.3 觸發相關 (Triggered Correlations) 28
4.4 資料探勘評估模型 31
伍、討論 33
陸、結論 35
參考文獻 (References) 37
附錄 39
Liberty Times, http://www.libertytimes.com.tw/index.htm
China Times, http://news.chinatimes.com/
Ahmad, A. and L. Dey, 2007, A k-mean clustering algorithm for mixed numeric and categorical data, Data &; knowledge Engineering 63, 503-527.
Bosch, J. and M. Hirschey, 1989, The valuation effects of corporate name changes, Financial Management 18, 64-73.
Chiu, C., H. G. Chi and R. J. Sung, 2011, The Hybrid of Genetic Algorithms and K-Prototypes Clustering Approach for Classification, Information Sciences
Cooper, M. J., H. Gulen, and P. R. Rau, 2005, Changing names with style: Mutual fund name changes and their effect on fund flows, Journal of Finance 60, 2825-2858.
Cooper, M., O. Dimitrov and P. Rau, 2001, A Rose.com by any other name, Journal of Finance 56, 2371-2388.
Davies J. R., D. Hillier and J. Thamm, 2007, Investor confusion and similarly identified securities, Accounting and Finance 47, 693-711.
Horng, S., M. Su, Y. Chen, T. Kao, R. Chen, J. Lai and C. D. Perkasa, 2011, A novel intrusion detection system based on hierarchical clustering and support vector machines, Expert Systems with Applications 38, 306-313.
Karpoff, J. and G. Rankine, 1994, In search of a signaling effect: the wealth effects of corporate name change, Journal of Banking and Finance 18, 1027–1045.
Kot, H. W., 2011, Corporate name changes: Price reactions and long-run performance, Pacific-Basin Finance Journal 19, 230-244.
Rashes, M., 2001, Massively confused investors making conspicuously ignorant choices (MCI-MCIC), Journal of Finance 56, 1911-1928.
Wu, Y., 2010, What's in a name? What leads a firm to change its name and what the new name foreshadows, Journal of Banking and Finance 34, 1344-1359.
Zhang, Y., Y. Dan, H. Chen, M. Thurmond and C. Larson, 2009, Automatic online news monitoring and classification for syndromic surveillance, Decision Support Systems 47, 508-517.
連結至畢業學校之論文網頁點我開啟連結
註: 此連結為研究生畢業學校所提供,不一定有電子全文可供下載,若連結有誤,請點選上方之〝勘誤回報〞功能,我們會盡快修正,謝謝!
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
無相關期刊