臺灣博碩士論文加值系統

台灣行動電信市場開放民營後蓬勃發展，行動電信產業屬特許行業，目前共有5家電信公司，激烈的市場競爭，造成電信業者營收下降。營業收入對行動電信業者營運策略、政府主管機關管理政策及投資人的投資決策十分重要，故準確預測營業收入是一個非常有意義的研究議題。然而，較少的研究著重在預測電信業營業收入，因此本文針對國內前三大行動電信業：台灣大哥大、中華電信、遠傳電信，收集每月各家電信業者的營業收入，運用自我迴歸整合移動平均(Autoregressive Integrated Moving Average, ARIMA)方法及類神經網路(Artificial Neural Network, ANN)、支援向量迴歸(Support Vector Regression, SVR)、極限學習機(Extreme Learning Machines , ELM)計算智能方法，建立預測模型。本文使用平均絕對百分比誤差(Mean Absolute Percentage Error , MAPE)來比較各預測模型準確性，研究結果顯示使用SVR方法所建立預測模型，其準確性優於使用ARIMA、ANN和ELM方法，研究成果可做為政府、電信業者及投資人決策參考。

The mobile telecommunications market in Taiwan is vigorous after opening up to private enterprises. The mobile telecommunications industry is a franchise industry and currently there are five telecommunications licensees. The competitive environment resulted in a decrease of operating revenue, which is a significant indicator of the operational strategies of mobile telecommunications operators, the management policies of government agencies, and investment decisions of investors. Accurately forecasting revenue is a very remarkable research topic. However, there is limited research on forecasting the revenue of mobile telecommunications operators. This article focuses on the top three mobile telecommunications companies in Taiwan: Taiwan Mobile Co., Chunghwa Telecom Co., and Far EasTone Telecommunications Co. To build predictive models, the monthly operating revenue of these operators is collected and following methods are applied: the Autoregressive Integrated Moving Average (ARIMA) method and computational intelligence methods, such as Artificial Neural Network (ANN), Support Vector Regression (SVR), and Extreme Learning Machines (ELM). Meanwhile, Mean Absolute Percentage Error (MAPE) is used to assess the accuracy of each model. The research results suggest that the SVR model produce a more accurate prediction of operating revenue than those using ARIMA, ANN, and ELM methods. The results can serve as a reference for government, telecommunications operators, and investors, decision making.

第壹章 緒論
第一節 研究背景
第二節 研究動機與目的
第三節 研究流程與架構
第貳章 文獻探討
第一節 時間序列之預測應用
第二節 類神經網路之預測應用
第三節 支援向量迴歸之預測應用
第四節 極限學習機之預測應用
第參章 研究方法
第一節 時間序列
第二節 類神經網路
第三節 支援向量迴歸
第四節 極限學習機
第肆章 實證研究
第一節 資料介紹
第二節 台灣大哥大預測分析
第三節 中華電信預測分析
第四節 遠傳電信預測分析
第五節 模型預測效能比較分析
第伍章 結論
第一節 研究發現
第二節 未來研究方向與建議
參考文獻

中文部分
丁誌榮 (2017)。運用時間序列與軟計算方法以預測台灣五家電信之申訴量。輔仁大學統計資訊學系應用統計碩士在職專班碩士論文 ，新北市。
吳昭霖 (2012)。應用SVR預測顧客流失之研究 － 以醫學美容產業為例。國立臺北大學資訊管理研究所碩士論文，台北市。
李天傑 (2016)。以倒傳遞類神經網路演算法預測電力消費量 －以台灣地區為例。國立中正大學通訊資訊數位學習碩士在職專班碩士論文，嘉義縣。
林雪蓮 (2010)。台灣電信產業營收淨額與營運資金供需預測之研究-X-12-ARIMA模型之應用。國立臺北大學企業管理學系碩士論文，新北市。
胡毓庭 (2017)。整合應用機器學習方法以分類多重輸入多重輸出系統之混合管制圖型樣。輔仁大學統計資訊學系應用統計碩士班碩士論文，新北市。
張宇丞 (2017)。展示型廣告之效益分析。元智大學資訊管理學系碩士論文，桃園市。
郭承林 (2012)。應用資料探勘技術建立顧客流失預測模型-以行動通訊產業為例。國立高雄應用科技大學企業管理系碩士論文，高雄市。
陳佳莉 (2017)。結合謹慎式粒子群演算法與對數最小平方支援向量機於死亡率預測。元智大學資訊管理學系博士論文，桃園市。
陳柏榕 (2015)。應用巨量資料分析建構一貫化鋼鐵廠之冷軋產品動態成本預測模型。東海大學工業工程與經營資訊學系碩士論文，台中市。
蔡宜珊 (2017)。台灣電力售電量預測之研究-使用ARIMA、機器學習與混合方法。輔仁大學統計資訊學系應用統計碩士在職專班碩士論文 ，新北市。
蕭仁滔 (2016)。開放陸客中轉對國籍航空公司運量變化之研究-以類神經網路建立預測模型。國立交通大學管理學院運輸物流學程碩士論文，新竹市。
簡壬申 (2017)。類神經網路在股票預測之獲利可能性研究 -以台灣50 成分股為例。國立雲林科技大學財務金融系碩士論文，雲林縣。
 
英文部分
Alon, I., Qi, M., & Sadowski, R. J. (2001). Forecasting aggregate retail sales. Journal of Retailing and Consumer Services, 8(3), 147-156.
Au, K. F., Choi, T. M., & Yu, Y. (2008). Fashion retail forecasting by evolutionary neural networks. International Journal of Production Economics, 114(2), 615-630.
Bianchi, L., Jarrett, J., & Hanumara, R. C. (1998). Improving forecasting for telemarketing centers by ARIMA modeling with intervention. International Journal of Forecasting, 14(4), 497-504.
Box, G. E., & Jenkins, G. M. (1970). Time series analysis, control, and forecasting. San Francisco, CA: Holden Day, 3226(3228), 10.
Chen, F. L., & Ou, T. Y. (2011). Sales forecasting system based on Gray extreme learning machine with Taguchi method in retail industry. Expert Systems with Applications, 38(3), 1336-1345.
Chen, K. Y., & Wang, C.-H. (2007). Support vector regression with genetic algorithms in forecasting tourism demand. Tourism Management, 28(1), 215-226.
Chen, X., Dong, Z. Y., Meng, K., Xu, Y., Wong, K. P., & Ngan, H. W. (2012). Electricity price forecasting with extreme learning machine and bootstrapping. IEEE Transactions on Power Systems, 27(4), 2055-2062.
Cheng, C. H., & Shiu, H. Y. (2014). A novel GA-SVR time series model based on selected indicators method for forecasting stock price. Information Science, Electronics and Electrical Engineering, 1, 395-399.
Co, H. C., & Boosarawongse, R. (2007). Forecasting Thailand’s rice export: Statistical techniques vs. artificial neural networks. Computers & Industrial Engineering, 53(4), 610-627.
Drucker, Harris; Burges, Christopher J. C.; Kaufman, Linda; Smola, Alexander J.; and Vapnik, Vladimir N. (1997).Support Vector Regression Machines, Advances in Neural Information Processing Systems9 .NIPS 1996, 155–161.
Ediger, V. Ş., & Akar, S. (2007). ARIMA forecasting of primary energy demand by fuel in Turkey. Energy Policy, 35(3), 1701-1708.
Farvaresh, H., & Sepehri, M. M. (2011). A data mining framework for detecting subscription fraud in telecommunication. Engineering Applications of Artificial Intelligence, 24(1), 182-194.
Hong, W.-C., Dong, Y., Chen, L.-Y., & Lai, C.-Y. (2010). Taiwanese 3G mobile phone demand forecasting by SVR with hybrid evolutionary algorithms. Expert Systems with Applications, 37(6), 4452-4462.
Huang, G.-B., Zhu, Q.-Y., & Siew, C.-K. (2006). Extreme learning machine: Theory and applications. Neurocomputing, 70(1-3), 489-501.
Huang, G. B., Chen, L., & Siew, C. K. (2006). Universal approximation using incremental constructive feedforward networks with random hidden nodes. IEEE Trans Neural Netw, 17(4), 879-892.
Huang, J., Bo, Y., & Wang, H. (2011). Electromechanical equipment state forecasting based on genetic algorithm – support vector regression. Expert Systems with Applications, 38(7), 8399-8402.
Kumar, U., & Jain, V. (2010). ARIMA forecasting of ambient air pollutants (O3, NO, NO2 and CO). Stochastic Environmental Research and Risk Assessment, 24(5), 751-760.
Lee, H., Lee, Y., Cho, H., Im, K., & Kim, Y. S. (2011). Mining churning behaviors and developing retention strategies based on a partial least squares (PLS) model. Decision Support Systems, 52(1), 207-216.
Lim, C., & McAleer, M. (2002). Time series forecasts of international travel demand for Australia. Tourism Management, 23(4), 389-396.
Lim, J., Nam, C., Kim, S., Rhee, H., Lee, E., & Lee, H. (2012). Forecasting 3G mobile subscription in China: A study based on stochastic frontier analysis and a Bass diffusion model. Telecommunications Policy, 36(10-11), 858-871.
Lin, C.-S. (2013). Forecasting and analyzing the competitive diffusion of mobile cellular broadband and fixed broadband in Taiwan with limited historical data. Economic Modelling, 35, 207-213.
Ljung, G. M., & Box, G. E. . (1978). On a measure of lack of fit in time series models. Biometrika, 65(2), 297–303.
Lu, C.-J., & Wang, Y.-W. (2010). Combining independent component analysis and growing hierarchical self-organizing maps with support vector regression in product demand forecasting. International Journal of Production Economics, 128(2), 603-613.
Lewis, C. D. (1982). Industrial and business forecasting methods: A practical guide to exponential smoothing and curve fitting. Butterworth Scientific, London.
Miao, D., Sun, W., Qin, X., & Wang, W. (2016). MSFS: Multiple Spatio-temporal Scales Traffic Forecasting in Mobile Cellular Network. 787-794.
Peng, Y., Lei, M., Li, J.-B., & Peng, X.-Y. (2014). A novel hybridization of echo state networks and multiplicative seasonal ARIMA model for mobile communication traffic series forecasting. Neural Computing and Applications, 24(3), 883-890.
Sokolov-Mladenović, S. M., Milos;Mladenović, Igor;Alizamir, Meysam. (2016). Economic growth forecasting by artificial neural network with extreme learning machine based on trade, import and export parameters. Computers in Human Behavior, 65, 43-45.
Sun, Z. L., Choi, T. M., Au, K. F., & Yu, Y. (2008). Sales forecasting using extreme learning machine with applications in fashion retailing. Decision Support Systems, 46(1), 411-419.
Vapnik, V.N.,Golowich, S.,Smola, A.J.,Mozer, M.,Jordan, M.,Petsche, T. (1997). Support vector method for function approximation, regression estimation, and signal processing. Advances in Neural Information Processing Systems, 9, 281–287.
Vhatkar, S., & Dias, J. (2016). Oral-care goods sales forecasting using artificial neural network model. Procedia Computer Science, 79, 238-243.
Wang, S. J., Huang, C. T., Wang, W. L., & Chen, Y. H. (2010). Incorporating ARIMA forecasting and service-level based replenishment in RFID-enabled supply chain. International Journal of Production Research, 48(9), 2655-2677.
Yadav, B., Ch, S., Mathur, S., & Adamowski, J. (2017). Assessing the suitability of extreme learning machines (ELM) for groundwater level prediction. Journal of Water and Land Development, 32(1).
Ye, X. (2010). The application of arima model in chinese mobile user prediction. Paper presented at the Granular Computing (GrC), 2010 IEEE International Conference on.
Yu, X., Qi, Z., & Zhao, Y. (2013). Support vector regression for newspaper/magazine sales forecasting. Procedia Computer Science, 17, 1055-1062.
Yu, Y., Choi, T. M., & Hui, C. L. (2011). An intelligent fast sales forecasting model for fashion products. Expert Systems with Applications, 38(6), 7373-7379.
Zhang, G., Eddy Patuwo, B., & Y. Hu, M. (1998). Forecasting with artificial neural networks:: The state of the art. International Journal of Forecasting, 14(1), 35-62.

網路資料
中華電信股份有限公司 http://www.cht.com.tw/
台灣大哥大股份有限公司https://www.taiwanmobile.com/
國家傳播委員會網站資料http://www.ncc.gov.tw/
遠傳電信股份有限公司 https://www.fetnet.net/