結合深度學習及關鍵字搜尋熱度趨勢於臺灣鋼筋價格漲跌幅之預測

HYBRIDIZING DEEP LEARNING WITH GOOGLE TRENDS TO PREDICT REBAR PRICE FLUCTUATION IN TAIWAN

10.6652/JoCICHE.202112_33(8).0001

馮重偉(Chung-Wei Feng)；江怡萱(Yi-Hsuan Chiang)

人工智慧 ； 卷積神經網路 ； Google trends ； 鋼筋價格 ； artificial intelligence ； convolutional neural network ； google trends ； rebar price

中國土木水利工程學刊

33卷8期（2021 / 12 / 01）

595 - 604

繁體中文

鋼筋價格受整體鋼鐵業影響，牽涉甚廣，導致漲跌狀況難預測。現有預估鋼鐵價格之資料庫或預測模型，多屬經濟取向預測難符合營建業需求。隨著電腦演算法的廣泛應用，人工智慧中的深度學習（Deep Learning）成為熱門主題，其中卷積神經網路（Convolutional Neural Network, CNN）能從大量的樣本獲取資料特徵以進行預測。因此本研究利用卷積神經網路建構預測價格漲跌模式，首先解析價格影響因子至數值資料項目，並考慮會造成影響的國內外事件，將蒐集之原始資料轉為圖片，作為模型訓練資料集。訓練完成之模型可利用新輸入之影響因子及關鍵字熱度資料執行鋼筋價格漲跌預測，最終實驗結果比較輸入不同事件關鍵字資料之預測模型準確率，提出預測鋼筋價格漲跌之卷積神經網路模型，期望提升實務工程鋼筋估價的準確性。

The fluctuation of the rebar price is hard to predict due to too many factors involved within the production of the steel industry. Current models and database for predicting the rebar price mainly focus on the economic performance, which is not suitable for construction industry. Along with the rapid application of the artificial intelligence technology, the deep learning concept is widely used in developing algorithms for predicting model. Convolutional neural network, the class of the deep learning, is good at extracting features from multidimensional data. Therefore, this research develops a convolutional neural network to predict the fluctuation of the rebar price. First, the factors including domestic and foreign events that could impact the rebar price are analyzed. Then the data of the above-mentioned factors are transformed into picture to train the proposed prediction model for rebar price. Finally, keywords that represent different events impact rebar price are used to calibrate the accuracy of the proposed model.

1. Andreas, Kaplan,Haenlein, Michael(2018).Siri, Siri in my hand, who's the fairest in the land? On the Interpretations, Illustrations and Implications of Artificial Intelligence.Bus. Horiz.,62,15-25.
2. Bhandare, Ashwin,Bhide, Maithili,Gokhale, Pranav,Chandavarkar, Rohan(2016).Applications of convolutional neural networks.IJCSIT,7,2206-2215.
3. Feng, Yuyao,Li, Guowen,Sun, Xiaolei,Li, Jianping(2019).Forecasting the number of inbound tourists with Google Trends.Procedia Comput, Sci.,162,628-633.
4. Guo, Jian-Feng,Ji, Qiang(2013).How does market concern derived from the Internet affect oil prices?.Appl. Energy,112,1536-1543.
5. Kulkarni1, Preeti,Londhe, Shreenivas,Deo, Makarand(2017).Artificial neural networks for construction management: A review.Soft Comput. in Civ. Eng.,1,70-88.
6. Liu, Zhishuo,Wang, Yongcong,Zhu, Shuang,Zhang, Baopeng,Wei, Lingyun(2014).Steel Prices Index Prediction in China Based on BP Neural Network.LISS,1,603-608.
7. Ma, Yiqun,Wang, Junhao(2019).Co-movement between oil, gas, coal, and iron ore prices, the Australian dollar, and the Chinese RMB exchange rates: A copula approach.Resour. Policy,63
8. Malanichev, A. G.,Vorobyev, P. V.(2011).Forecast of global steel prices.Studies on Russian Economic Development,22,304-311.
9. Moghaddam, Mohammad Reza,Manfezi, Masood,Danesh, Amir Hossein Mehr,Kakha, Gholamhassan(2014).Prediction of monthly price of iron ore by using artificial neural network.Indian J. of Sci. Res.,1,200-1204.
10. Nielsen,Michael, A.(2015).Neural Networks and Deep Learning.Australia:
11. Pustov, Alexander,Malanichev, Alexander,Khobotilov, Ilya(2013).Long-term iron ore price modeling: Marginal costs vs. incentive price.Resour. Policy,38(4),558-567.
12. Sharma, Sumana(2008).Virginia Commonwealth University.
13. Sharma, Sumana,Osei-Bryson, Kweku-Muata,Kasper, George M.(2012).Evaluation of an integrated knowledge discovery and data mining process model.Expert Syst. with Appl.,39,11335-11348.
14. Shin, Soo-Yong,Seo, Dong-Woo,An, Jisun,Kwak, Haewoon,Kim, Sung-Han,Gwack, Jin(2016).High correlation of Middle East respiratory syndrome spread with Google search and Twitter trends in Korea.Sci. Rep.,6
15. Su, Chi-Wei,Wang, Kai-Hua,Chang, Hsu-Ling,Dumitrescu–Peculea, Adelina(2017).Do iron ore price bubbles occur?.Resour. Policy,53,340-346.
16. Tsai, Yun-Cheng,Chen, Jun-Hao,Wang, Jun-Jie(2018).Predict forex trend via convolutional neural networks.Journal of Intelligent Systems,29(1)
17. Williams, Trefor P.,Gong, Jie(2014).Predicting construction cost overruns using text mining, numerical data and ensemble classifiers.Autom. in Constr.,43,23-29.
18. Wu, Hao,Zhao, Jinsong(2018).Deep convolutional neural network model based chemical process fault diagnosis.Comput. and Chem. Eng.,115,185-197.
19. 王勝榮(2019)。國立成功大學土木工程學研究所。
20. 李倩瑜(2014)。國立臺北科技大學工業工程與管理系碩士班。
21. 林大貴(2017).深度學習人工智慧實務應用.新北市:博碩文化.
22. 林秀貞(2007)。國立中央大學土木工程研究所。
23. 許鈞甯(2009)。國立成功大學經營管理碩士學位學程。
24. 陳建任(2011).台灣鋼鐵產業發展趨勢與鋼價展望.金屬工業研究發展中心.
25. 陳建任(2014).全球化競爭趨勢下,我國鋼鐵產業的主要挑戰與因應策略.金屬工業研究發展中心.