簡易檢索 / 詳目顯示

研究生: 黃敏惠
Huang, Min-Huei
論文名稱: 應用隨機森林演算法以某產業園區配水量預測台灣股票指數
Forecasting Taiwan Stock Index through Random Forest Algorithm by Using Water Consumption in an Industrial Park
指導教授: 周榮華
Chou, Jung-Hua
學位類別: 碩士
Master
系所名稱: 工學院 - 工程科學系碩士在職專班
Department of Engineering Science (on the job class)
論文出版年: 2023
畢業學年度: 111
語文別: 中文
論文頁數: 60
中文關鍵詞: 用水量股價指數預測隨機森林
外文關鍵詞: Water consumption, Stock market prediction, Random Forest
相關次數: 點閱:216下載:9
分享至:
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報
  • 水資源為工業製程中重要的生產要素之一,本研究嘗試從水資源的消耗量推估經濟發展,應用隨機森林演算法,以某產業園區的配水量變化預測台灣股票指數趨勢。股票指數以與園區產業最相關的電子類報酬指數為主,並細分8個產業類別分項進行預測,包含半導體類、電腦及週邊設備類、光電類、通信網路類、電子零組件類、電子通路類、資訊服務類與其他電子類,模型亦延伸預測整體市場變化(發行量加權股價指數)。
    以配水量作為領先指標,透過投入60日的配水量數據以預測單日股票指數。研究結果發現,配水量與股票指數間的遞延關係多落在4-5個月或7-8個月,在預測效果上,對於電子類報酬指數與整體市場皆有不錯成效,模型的決定係數皆大於0.8,驗證集與測試集之MAPE皆小於10 %,顯見該產業園區配水量對於電子類產業及整體市場具備預測能力。模型成效最佳者為資訊服務類,測試集MAPE達1.44 %。與園區配水量最直接相關的產業屬半導體業與光電業,光電業卻因相關係數接近於零,顯見兩者相關性低,不適合建立預測模型。

    In this study, the Taiwan stock index is predicted from the water consumption in an industrial park by the random forest algorithm. As water consumption may not reflect the stock change instantly, the correlation between the stock index and water consumption is used to determine the number of months by which the stock index may lag behind. The data was divided into training, validation, and testing sets; the random forest model was trained using a 60-day dataset of water consumption to predict the daily stock index.
    The research findings reveal that there is a deferred relationship between water consumption and the stock index, mostly falling within 4-5 months or 7-8 months. The model demonstrates good performance across various market types, with Rd2 being greater than 0.8. The mean absolute percentage error (MAPE) for both validation and testing sets is below 10 %. This indicates that water consumption in the industrial park can effectively predict the Electronics Index and the overall market (TAIEX Total Return Index).

    摘要 I Extended Abstract II 誌謝 VII 目錄 VIII 表目錄 X 圖目錄 XI 第一章 緒論 1 1.1 研究動機 1 1.2 研究目的 2 1.3 研究限制 4 1.4 研究架構 4 第二章 文獻探討 6 2.1 工業用水與經濟發展 6 2.1.1 環境庫茲涅茨曲線 6 2.1.2 水足跡 8 2.1.3 國內環境 9 2.2 產業園區介紹 11 2.2.1 產業類型 11 2.2.2 配水量 13 2.2.3 營業額 14 2.3 股票預測研究 14 第三章 研究方法 17 3.1 研究流程及架構 17 3.2 資料集建立 18 3.3 資料預處理 19 3.3.1 正規化 19 3.3.2 缺失值處理 22 3.4 模型建立 23 3.5 模型評估指標 24 第四章 結果與討論 26 4.1 配水量與股票指數之關係 26 4.1.1 遞延關係 26 4.1.2 分群關係 28 4.2 日配水量投入量 29 4.3 股票指數預測模型 31 4.3.1 電子類報酬指數 33 4.3.2 發行量加權股價指數 45 4.4 討論 47 4.4.1 光電類與配水量關係 48 4.4.2 半導體類的預測效果 49 4.4.3 半導體業與光電業的外溢效應 52 第五章 結論與建議 54 5.1 結論 54 5.2 研究建議 55

    [1]C. F. Murphy, G. A. Kenig, D. T. Allen, J. P. Laurent, and D. E. Dyer, "Development of parametric material, energy, and emission inventories for wafer fabrication in the semiconductor industry," Environ Sci Technol, vol. 37, no. 23, pp. 5373-82, Dec 1 2003, doi: 10.1021/es034434g.
    [2]K. Frost and I. Hua, "Quantifying spatiotemporal impacts of the interaction of water scarcity and water use by the global semiconductor manufacturing industry," Water Resources and Industry, vol. 22, p. 100115, 2019.
    [3]經濟部水利署, 逢甲大學, Ed. 110年用水統計年報彙編, 逢甲大學 ed. 經濟部水利署, 2022, pp. B-10.
    [4]臺灣證券交易所. "臺灣證券交易所發行量加權股價指數." 臺灣證券交易所. https://www.taifex.com.tw/cht/2/weightedPriceIndex (accessed 5/21, 2023).
    [5]臺灣證券交易所. 臺灣證券交易所發行量加權股價指數編製要點, 2023.
    [6]G. M. Grossman and A. B. Krueger, "Economic growth and the environment," The Quarterly Journal of Economics, vol. 110, no. 2, pp. 353-377, 1995.
    [7]D. I. Stern, "The rise and fall of the environmental Kuznets curve," World development, vol. 32, no. 8, pp. 1419-1439, 2004.
    [8]I. Cazcarro, R. Duarte, and J. Sánchez-Chóliz, "Economic growth and the evolution of water consumption in Spain: A structural decomposition analysis," Ecological Economics, vol. 96, pp. 51-61, 2013.
    [9]E. Tello and J. R. Ostos, "Water consumption in Barcelona and its regional environmental imprint: a long-term history (1717–2008)," Regional Environmental Change, vol. 12, pp. 347-361, 2012.
    [10]R. Duarte, V. Pinilla, and A. Serrano, "Looking backward to look forward: water use and economic growth from a long-term perspective," Applied Economics, vol. 46, no. 2, pp. 212-224, 2014.
    [11]R. Duarte, V. Pinilla, and A. Serrano, "Is there an environmental Kuznets curve for water use? A panel smooth transition regression approach," Economic Modelling, vol. 31, pp. 518-527, 2013.
    [12]A. Hemati, M. Mehrara, and A. Sayehmiri, "New vision on the relationship between income and water withdrawal in industry sector," Natural Resources, vol. 2, no. 03, p. 191, 2011.
    [13]E. Sanyé-Mengual, M. Secchi, S. Corrado, A. Beylot, and S. Sala, "Assessing the decoupling of economic growth from environmental impacts in the European Union: A consumption-based approach," Journal of Cleaner Production, vol. 236, p. 117535, 2019.
    [14]F. Dalstein and A. Naqvi, "21st century water withdrawal decoupling: A pathway to a more water-wise world?," Water Resources and Economics, vol. 38, p. 100197, 2022.
    [15]M. A. Montoya, G. Allegretti, L. A. S. Bertussi, and E. Talamini, "Domestic and foreign decoupling of economic growth and water consumption and its driving factors in the Brazilian economy," Ecological Economics, vol. 206, p. 107737, 2023.
    [16]w. f. network. "What is water footprint?" https://www.waterfootprint.org/water-footprint-2/what-is-a-water-footprint/ (accessed 5/27, 2023).
    [17]A. Y. Hoekstra and A. K. Chapagain, "Water footprints of nations: water use by people as a function of their consumption pattern," Water Resources Management, vol. 21, pp. 35-48, 2007.
    [18]M. Mekonnen and A. Y. Hoekstra, "National water footprint accounts: The green, blue and grey water footprint of production and consumption. Volume 1: Main Report," 2011.
    [19]行政院主計總處. (2023). 國民所得統計摘要.
    [20]行政院主計總處. (2023). 國民所得統計年報.
    [21]W.-C. Lu, "Electricity consumption and economic growth: Evidence from 17 Taiwanese industries," Sustainability, vol. 9, no. 1, p. 50, 2016.
    [22]黃盈如, "經濟成長、二氧化碳排放、能源消耗、核能與再生能源消耗之實證分析-以台灣為例," 碩士, 經濟學研究所, 國立中山大學, 高雄市, 2017. [Online]. Available: https://hdl.handle.net/11296/44e2w9
    [23]台灣自來水股份有限公司. (2023). 台灣自來水事業統計年報中華民國111年.
    [24]中華民國行政院主計總處. 國民所得及經濟成長統計資料庫 [Online] Available: https://nstatdb.dgbas.gov.tw/dgbasAll/webMain.aspx?sys=100&funid=dgmaind (accessed 5/27, 2023).
    [25]陳坤成, "產業群聚與企業經營模式關聯性之探討—以臺灣精密機械產業為例," 博士, 科技管理研究所, 國立交通大學, 新竹市, 2007. [Online]. Available: https://hdl.handle.net/11296/3vq88j
    [26]林季蓉, "臺灣科學園區產業群聚之研究," (in 繁體中文), 創新研發學刊, vol. 5, no. 2, pp. 48-60, 2009, doi: 10.30080/jird.200912.0004.
    [27]行政院主計總處. (2021). 行業統計分類(第11次修正).
    [28]經濟部商業司. 經濟部商業司 [Online] Available: https://findbiz.nat.gov.tw/fts/query/QueryBar/queryInit.do (accessed 4/10, 2023).
    [29]經濟部工業局. "歷年營運中工廠家數." 經濟部工業局. https://serv.gcis.nat.gov.tw/RDownLoad/DownLoad.jsp (accessed 5/28, 2023).
    [30]經濟部水利署. 經濟部水利署各項用水統計資料庫 [Online] Available: https://wuss.wra.gov.tw/annuals.aspx (accessed 5/28, 2023).
    [31]R. C. Cavalcante, R. C. Brasileiro, V. L. F. Souza, J. P. Nobrega, and A. L. I. Oliveira, "Computational Intelligence and Financial Markets: A Survey and Future Directions," Expert Systems with Applications, vol. 55, pp. 194-211, 2016/08/15/ 2016, doi: https://doi.org/10.1016/j.eswa.2016.02.006.
    [32]T. O. Kehinde, F. T. S. Chan, and S. H. Chung, "Scientometric review and analysis of recent approaches to stock market forecasting: Two decades survey," Expert Systems with Applications, vol. 213, p. 119299, 2023/03/01/ 2023, doi: https://doi.org/10.1016/j.eswa.2022.119299.
    [33]O. Bustos and A. Pomares-Quimbaya, "Stock market movement forecast: A systematic review," Expert Systems with Applications, vol. 156, p. 113464, 2020.
    [34]M. M. Kumbure, C. Lohrmann, P. Luukka, and J. Porras, "Machine learning techniques and data for stock market forecasting: A literature review," Expert Systems with Applications, p. 116659, 2022.
    [35]C. Zhang, N. N. Sjarif, and R. B. Ibrahim, "Decision fusion for stock market prediction: a systematic review," IEEE Access, vol. 10, pp. 81364-81379, 2022, doi: 10.1109/ACCESS.2022.3195942.
    [36]L. Breiman, "Random forests," Machine learning, vol. 45, pp. 5-32, 2001.
    [37]G. Biau and E. Scornet, "A random forest guided tour," TEST, vol. 25, no. 2, pp. 197-227, 2016/06/01 2016, doi: 10.1007/s11749-016-0481-7.
    [38]TIP臺灣指數股份有限公司. 發行量加權股價指數系列指數歷史指數值 [Online] Available: https://taiwanindex.com.tw/indexes/multipleHistory (accessed 4/8, 2023).
    [39]台灣自來水股份有限公司, 百年大旱 台水抗旱特輯(109年7月-110年8月). 台中市: 台灣自來水股份有限公司, 2021, pp. 107-108.
    [40]中華民國國家發展委員會. 製造業採購經理人指數(PMI)-(細項指數) [Online] Available: https://index.ndc.gov.tw/n/zh_tw/data/PMI/index#/ .
    [41]財團法人工業技術研究院, "太陽光電產業2022-2024專業人才需求推估調查," 2021.
    [42]林穎毅, "台灣光電產業之轉捩點," (in 繁體中文;英文), 光連:光電產業與技術情報, no. 169, pp. 14-19, 2022.
    [43]G. W. Brown and M. T. Cliff, "Investor sentiment and the near-term stock market," Journal of Empirical Finance, vol. 11, no. 1, pp. 1-27, 2004/01/01/ 2004, doi: https://doi.org/10.1016/j.jempfin.2002.12.001.
    [44]M. Baker and J. Wurgler, "Investor sentiment in the stock market," Journal of Economic Perspectives, vol. 21, no. 2, pp. 129-152, 2007, doi: 10.1257/jep.21.2.129.
    [45]N. Barberis, A. Shleifer, and R. Vishny, "A model of investor sentiment," Journal of Financial Economics, vol. 49, no. 3, pp. 307-343, 1998/09/01/ 1998, doi: https://doi.org/10.1016/S0304-405X(98)00027-0.
    [46]K.-H. Choi and S.-M. Yoon, "Investor sentiment and herding behavior in the korean stock market," International Journal of Financial Studies, vol. 8, no. 2, p. 34, 2020. [Online]. Available: https://www.mdpi.com/2227-7072/8/2/34.
    [47]臺灣證卷交易所, "【歷年證券交易量值總表】年報," 臺灣證卷交易所, 2023.
    [48]臺灣證卷交易所, "【產業別股票交易統計表】月報," 臺灣證卷交易所, 2023.
    [49]行政院主計總處. (2020). 產業關聯統計編制報告民國105年. [Online] Available: https://www.stat.gov.tw/lp.asp?ctNode=2107&CtUnit=1038&BaseDSD=7&mp=4

    無法下載圖示 校內:立即公開
    校外:2028-08-24公開
    電子論文尚未授權公開,紙本請查館藏目錄
    QR CODE