隨著現今科技的進步，數據產生的速度越來越快速，數據量也越來越龐大，大數據的概念也從3Vs進展到了5Vs。而人工智慧、機器學習與雲端計算在數據研究中扮演非常重要的角色。本研究主要焦點在以金融大數據在TensorFlow與Keras上來建模與匯率預測，並且利用Minitab來做結果的分析。
在此研究裡，我們分成兩個階段，第一階段為數據預測，首先將收集到的匯率資料轉換成可用的格式與進行正規化，預處理完後，以TensorFlow做為後端引擎，利用Keras建造一個用於預測匯率的一維卷積類神經網路模型，其中利用了滑動窗格法來劃分訓練集與驗證集，並藉由實驗設計來調整模型參數，接著做預測，以測試集的部分來做績效評估。 第二階段為結果分析，我們將一部分的歷史數據結合預測結果投入到Minitab中，以雙樣本t檢定來檢定上一年與下一年是否有顯著差異，經研究分析後希望推測分析不同時間區段的匯率操控國。在未來，此資料不僅侷限於此個案資料，可以加入更多匯率影響因素資料以達到分析完整性。

With the advancement of today's technology, the speed of data generation is getting faster and the amount of data is getting larger. The concepts of Big Data have progressed from 3Vs to 5Vs. Nowadays, Artificial Intelligence, Machine Learning and Cloud Computing play important roles in data science. In this thesis, we focused on exchange rate prediction from financial Big Data with TensorFlow and Keras, and used Minitab to analyze the results.
In this study, we divided the research process into two phases. The first phase was data prediction. First, data preprocessing converted the collected exchange rate data into a usable format and normalization. After preprocessing, we divided the data into training, validation and testing data sets. Next step, we used TensorFlow as the back-end engine in Keras to construct a one-dimensional Convolutional Neural Network (CNN) model with a sliding window for predicting exchange rate. We selected the model parameters by the design of experiment method. After choosing the best parameters for the CNN model, we used the testing data set to do the performance evaluation. Finally, we forecasted the exchange rate for 2 years. The second phase was the result analysis. We put historical data combined with the prediction values into Minitab software and used the two-sample t test to check whether there was a significant difference between the previous year and the next year. After analysis, we could exam which period and which country control the exchange rate. Furthermore, this modeling process was not limited to this case data, and more influencing factors of the exchange rate could be added in this study to achieve analytical integrity.

C. C. Austin (2018). "A path to Big Data readiness." The 2018 IEEE International Conference on Big Data, 4844–4853.
S. K. Aggarwal and M. Kumar (2016). "ANN based residential demand forecasting using weather and special day information." The 2016 India International Conference on Power Electronics (IICPE), 1–5.
A. V. Bataev (2018). "Analysis of the application of Big Data technologies in the financial sphere." The 2018 IEEE International Conference Quality Management, Transport and Information Security, Information Technologies (IT&QM&IS), 568–572.
S. Bokov. (2018). Exchange rate data source. From https://tw.tradingview.com/.
(2018-12-28).
J. F. Chen, W. L. Chen, C. P. Huang, S. H. Huang and A. P. Chen (2016). "Financial time-series data analysis using deep convolutional neural networks." The 2016 International Conference on Cloud Computing and Big Data (CCBD), 87–92.
Y. Demchenko, C. de Laat and P. Membrey (2014). "Defining architecture components of the Big Data ecosystem." The 2014 International Conference on Collaboration Technologies and Systems (CTS), 104–112.
A. C. Das, S. N. Mohanty, A. G. Prasad and A. Swain (2016). "A model for detecting and managing unrecognized data in a Big Data framework." The 2016 International Conference on Electrical, Electronics, and Optimization Techniques (ICEEOT), 3517–3522.
T. Dong, B. Yang and T. Tian (2015). "Volatility analysis of China stock market using high-frequency financial Big Data." The 2015 IEEE International Conference on Smart City/SocialCom/SustainCom (SmartCity), 769–774.
L. Feng and J. Z. Zhang (2010). "Application of ANN in forecast of surface runoff." The 6th International Conference on Networked Computing, 1–3.
J. Gan, W. Wang and K. Lu (2019). "A new perspective: Recognizing online handwritten China characters via 1-dimensional CNN." Information Sciences, 478, 375–390.
T. Hosaka (2019). "Bankruptcy prediction using imaged financial ratios and convolutional neural networks." Expert Systems with Applications, 177, 287–299.
E. Hoseinzade and S. Haratizadeh (2019). "CNNpred: CNN-based stock market prediction using a diverse set of variables." Expert Systems with Applications, 129, 273–285.
S. Khatoon, I. Nasiruddin, A. Kr. Singh and Priti (2015). "ANN based electric load forecasting applied to real time data." The 2015 Annual IEEE India Conference, 1–5.
D. Laney (2001). "3-D data management: Controlling data volume, velocity, and variety." File: 949 Addendum, META Group. From: https://blogs.gartner.com/doug-laney/files/2012/01/ad949-3D-Data-Management-Controlling-Data-Volume-Velocity-and-Variety.pdf. (2019-4-05).
A. Lasfer, H. El-Baz and I. Zualkernan (2013). "Neural network design parameters for forecasting financial time series." The 2013 International Conference on Modeling, Simulation and Applied Optimization (ICMSAO), 1–4.
C. K. S. Leung, F. Jiang, H. Zhang, and A. G. M. Pazdor (2016). "A data science model for Big Data analytics of frequent patterns." IEEE, 14th International Conference on Dependable, Autonomic and Secure Computing, 14th International Conference on Pervasive Intelligence and Computing, 2nd International Conference on Big Data Intelligence and Computing and Cyber Science and Technology Congress, 866–873.
C. Y. Lee and V. W. Soo (2017). The "Predict stock price with financial news based on recurrent convolutional neural networks." The 2017 Conference on Technologies and Applications of Artificial Intelligence, 160–165.
A. Lee, M. C. Wu, A. P. Chen (2016). "Treand behavior research by pattern analysis in financial Big Data - a case study of taiwan index futures market." The 2016 International Conference on Cloud Computing and Big Data, 162–165.
McKinsey & Company (2011). "Big Data: The next frontier for innovation, competition, and productivity." From https://bigdatawg.nist.gov/pdf/MGI_big_data_full_report.pdf. (2019-4-10).
McKinsey & Company (2013). "Value potential of Big Data affects virtually." From https://www.slideshare.net/McK_CMSOForum/customer-journey-analytics-and-big-data/4-McKinsey_Company_3Value_potential_of. (2019-4-10).
McKinsey & Company (2018). "Top 10 insights of 2018." From https://www.mckinsey.com/about-us/new-at-mckinsey-blog/top-10-insights-of-2018.
(2019-4-10).
V. E. Neagoe, A. D. Ciotec and G. S. Cucu (2018). "Deep convolutional neural networks versus multilayer perceptron for financial prediction." The 2018 International Conference on Communications, 201–206.
NN SVG. From http://alexlenail.me/NN-SVG/LeNet.html. (2019-5-10).
K. R. Nair, V. Vanitha and M. Jisma (2017). "Forecasting of wind speed using ANN, ARIMA and Hybrid models." The 2017 International Conference on Intelligent Computing, Instrumentation and Control Technologies, 170–175.
L. Ni,Y. Li, X.Wang, J. Zhang, J. Yu and C. Qi (2019). "Forecasting of forex time series data based on deep learning." Procedia Computer Science, 147, 647–652.
M. Paryasto, A. Alamsyah, B. Rahardjo and Kuspriyanto (2014). "Big-data security management issues." The 2014 International Conference on Information and Communication Technology (ICoICT), 59 – 63.
S. Pervaiz, I. Deiab, S. Zafar and S. Shams (2012). "Prediction of energy consumption and surface roughness in reaming operation of Al-6061using ANN based models." The 2012 International Conference of Robotics and Artificial Intelligence, 169–173.
S. Parise, B. Iyer and D. Vesset (2013). "Four Strategies to Capture and Create Value from Big Data." Ivey Business Journal. 76(4), 1–5.
A. E. Permanasari, D. R. A. Rambli and P. D. D. Dominic (2010). "Forecasting of salmonellosis incidence in human using artificial neural network (ANN)." The 2nd International Conference on Computer and Automation Engineering, 1, 34–41.
T. A. Runkler (2016). Data Analytics - Models and Algorithms for Intelligent Data Analysis, 2nd Edition, Springer Vieweg.
D. Snyder and B. Burress (2011). "Managing and analyzing large data sets." The 2011 Future of Instrumentation International Workshop Proceedings, 71–74.
N. Srivastava, G. Hinton, A. Krizhevsky, I. Sutskever and R. Salakhutdinov (2014). "Dropout: A simple way to prevent neural networks from overfitting." Journal of Machine Learning Research, 15, 1929–1958.
O. B. Sezer and A. M. Ozbayoglu (2018). "Algorithmic financial trading with deep convolutional neural networks: Time series to image conversion approach." Applied Soft Computing, 70, 525–538.
M. S. Sabitha, S. Viayalakshmi, R. M. R. Sre (2016). "Big Data management system for the harmonization of enterprise model." The 2016 International Conference on Computing Technologies and Intelligent Data Engineering, 1–6.
R. H. Tsaih, B. S. Kuo, T. H. Lin and C. C. Hsu (2018). "The use of Big Data analytics to predict the foreign exchange rate based on public media: A machine-learning experiment." IT Professional, 20, 34–41.
A. Tsantekidis, N. Passalis, A. Tefas, J. Kanniainen, M. Gabbouj and A. Iosifidis (2017). "Forecasting stock prices from the limit order book using convolutional neural networks." The 2017 Conference on Business Informatics, 1, 7–12.
J. Wang, Z. Yin, C. Miao, W. Wei, Y. Zhao and Y. Wu (2010). "The application of artificial neural network on forecast of meiyu rainfall at lower Yangtze River Valley." The 2010 6 International Conference on Natural Computation, 4, 1887–1981.
Y. Yang, Y. Yang and J. Li (2016). "Research on financial time series forecasting based on SVM." The 2016 International Computer Conference on Wavelet Active Media Technology and Information Processing, 346–349.
G. Zhang, Q. Li, Q. Luo and Z. Zhou (2009). "High frequency financial time series forecasting via particle filtering." The 2009 International Conference on Information Management, Innovation Management and Industrial Engineering, 4, 62–65.
J. Zhang, Y. Chen and T. Li (2013). "Opportunities of innovation under challenges of Big Data." The 10th International Conference on Fuzzy Systems and Knowledge Discovery, 669–673.
Y. Zhang and Q. Li (2018). "A regressive convolution neural network and support vector regression model for electricity consumption forecasting." Future of Information and Communications Conference 2019, 2, 1–14.
Thomson Reuters (APRIL 14, 2010 / 3:15 PM), 「〔重要历程〕人民币汇率的前世今生」, 取自https://www.reuters.com/article/idCNnCN098325720100414.
擷取日期:2019年2月25號.
許嘉棟 (2018),台灣銀行家雜誌第102期. 「人民銀行干預下的人民幣匯率」, 取自http://service.tabf.org.tw/TTB/Article/Detail?aID=127.
擷取日期:2019年2月25號.
鉅亨網新聞中心※來源：新華社中國金融信息網 (2016/08/09 08:51). 「811匯改一周年人民幣匯率市場化程度提高」,取自https://news.cnyes.com/news/id/2143911. 擷取日期:2019年2月25號.