在自由競爭的市場下，市場佔有率對企業活動及戰略規劃是很重要的參考指標，市場佔有率較高的企業在市場中擁有較大的競爭優勢與規模經濟，在供應鏈各個階段也都可能因其市場佔有率較高而獲得較多折扣。隨著技術的發展，消費者透過網路便可完成商品的購買，各種購物型態的出現與先前的購物方式形成了競爭關係。在競爭激烈且市場資訊難以取得的市場中，若能提早得知不同購物型態的未來趨勢，對企業經營者在進行管理決策上有很大的參考價值。市場佔有率歷史資料的形成為一時間序列，傳統的預測方法多為迴歸模型，除了要選擇合適的自變數外，自變數本身也要對市場佔有率的增減產生影響，在眾多自變數的選擇中，很難考慮到所有影響因素，即使考慮了足夠的影響因素，若自變數的數量過多，也可能造成求解模型參數的計算時間過長、模型過於龐大或是使用模型的成本過高等情況。本研究欲以與市場佔有率相關的市場銷售額歷史數據為對象，先使用田口方法實驗找出影響模型的噪音與可控制因子間超參數的最佳組合後，將上述方法得到的結果對長短期記憶網路進行設置，透過利用HP濾波器(Hodrick–Prescott filter, HP filter)將帶有長期趨勢的市場銷售額歷史資料拆解成趨勢性特徵與週期性特徵，藉由長短期記憶網路學習對此二特徵的學習，對未來一段時間內的市場佔有率趨勢進行預測，最後與其他模型結果進行比較，使其能獲得更準確的結果。透過實際的零售業資料進行驗證，使用不同的競爭組合對其總銷售進行預測，再將預測結果換算成市場佔有率，發現傳統迴歸模型雖然在市場佔有率方面有良好的預測結果，但在總銷售額的預測上為本研究所提出的預測方法較佳。在實際驗證中，本研究所設計的資料收集方式預測結果較未經過設計來得佳，可以說明本研究所提供的預測流程能有效得提升模型準確度，且可以用於不同時間序列的資料集中。而在資料集樣本數較少的情況下，本研究所提出預測市場佔有率的流程能解決資料取得不易而未能及時掌握變化趨勢的問題。

The prediction of market shares is an important reference for enterprises to comprehend their future competitiveness and to formulate better management strategies. Nowadays, when it comes to predict market shares, the most common method is regression; however, since numerous factors are affecting the market shares, it is difficult to choose an appropriate number of independent variables in the model. If we choose excessive factors in the model construction, it may take long time to solve the model, which leads to an increased cost. In contrast, choosing insufficient factors may result in an inaccurate prediction. Therefore, the purpose of this study is to propose a prediction framework with a deep learning approach, which only take revenue into account while omitting choosing the numbers of independent variables, to improve the accuracy of predicting.
In our research, we use Taguchi methods and deep learning in predicting procedure. Firstly, we employ Taguchi method to optimize the configuration of neural networks for predicting revenue, then analyze the effect of each designed hyperparameter. Secondly, we build LSTM with hyperparameters obtained from the previous step. In order to improve the accuracy of the prediction, we use the Hodrick–Prescott filter to divide each format of the revenue data into two individual components, seasonal data and trend data, respectively. The prediction framework is tested by using the revenue data of different objects, and we use mean absolute error (MAE) and mean absolute percentage error (MAPE) to evaluate its performance. Furthermore, we compare the framework with other prediction methods. The results show that this prediction framework has the best performances among different prediction methods and it achieves the purpose of only using the revenue to predict market shares.

R. E. Burnkrant and A. Cousineau, "Informational and Normative Social Influence in Buyer Behavior," Journal of Consumer Research, vol. 2, no. 3, pp. 206-215, 1975.
R. D. Buzzell, B. T. Gale, and R. G. Sultan, "Market Share-a Key to Profitability," Harvard Business Review, vol. 53, no. 1, pp. 97-106, 1975.
A. O. Hirschman, National Power and the Structure of Foreign Trade. Univ of California Press, 1980.
F. M. Scherer and D. Ross, "Industrial Market Structure and Economic Performance, Boston," MA: Houghton Mufflin, 1990.
C. A. Sims, "Macroeconomics and Reality," Econometrica: Journal of the Econometric Society, pp. 1-48, 1980.
G. E. Box, G. M. Jenkins, G. C. Reinsel, and G. M. Ljung, Time Series Analysis: Forecasting and Control. John Wiley & Sons, 2015.
H. Akaike, "A New Look at the Statistical Model Identification," IEEE Transactions on Automatic Control, vol. 19, no. 6, pp. 716-723, 1974.
I. Alon, M. Qi, and R. J. Sadowski, "Forecasting Aggregate Retail Sales:: A Comparison of Artificial Neural Networks and Traditional Methods," Journal of retailing and consumer services, vol. 8, no. 3, pp. 147-156, 2001.
J. S. Armstrong and J. U. Farley, "A Note on the Use of Markov Chains in Forecasting Store Choice," Management Science, vol. 16, no. 4, 1969.
A. Ezzati, "Forecasting Market Shares of Alternative Home-Heating Units by Markov Process Using Transition Probabilities Estimated from Aggregate Time Series Data," (in English), Management Science Series B-Application, Article vol. 21, no. 4, pp. 462-473, 1974, doi: 10.1287/mnsc.21.4.462.
E. Bridges, C. K. B. Yim, and R. A. Briesch, "A High-Tech Product Market Share Model with Customer Expectations," (in English), Marketing Science, Article vol. 14, no. 1, pp. 61-81, Win 1995, doi: 10.1287/mksc.14.1.61.
D. E. Sexton Jr, "Estimating Marketing Policy Effects on Sales of a Frequently Purchased Product," Journal of Marketing Research, vol. 7, no. 3, pp. 338-347, 1970.
P. A. Naert and A. Bultez, "Logically Consistent Market Share Models," Journal of Marketing Research, vol. 10, no. 3, pp. 334-340, 1973.
R. Brodie and C. A. De Kluyver, "Attraction Versus Linear and Multiplicative Market Share Models: An Empirical Evaluation," Journal of Marketing Research, vol. 21, no. 2, pp. 194-201, 1984.
H. C. Hung, Y. S. Tsai, and M. C. Wu, "A Modified Lotka-Volterra Model for Competition Forecasting in Taiwan's Retail Industry," (in English), Computers & Industrial Engineering, Article vol. 77, pp. 70-79, Nov 2014, doi: 10.1016/j.cie.2014.09.010.
H.-C. Hung, Y.-C. Chiu, H.-C. Huang, and M.-C. Wu, "An Enhanced Application of Lotka–Volterra Model to Forecast the Sales of Two Competing Retail Formats," Computers & Industrial Engineering, vol. 109, pp. 325-334, 2017.
V. Kumar, A. Nagpal, and R. Venkatesan, "Forecasting Category Sales and Market Share for Wireless Telephone Subscribers: A Combined Approach," International Journal of Forecasting, vol. 18, no. 4, pp. 583-603, 2002.
C.-I. Hsu, Y.-C. Huang, and K. I. Wong, "A Grey Hybrid Model with Industry Share for the Forecasting of Cargo Volumes and Dynamic Industrial Changes," Transportation Letters, vol. 12, no. 1, pp. 25-36, 2020.
F. Rosenblatt, "The Perceptron: A Probabilistic Model for Information Storage and Organization in the Brain," Psychological Review, vol. 65, no. 6, p. 386, 1958.
A. B. Arrieta et al., "Explainable Artificial Intelligence (Xai): Concepts, Taxonomies, Opportunities and Challenges toward Responsible Ai," Information Fusion, vol. 58, pp. 82-115, 2020.
Y. Lecun, L. Bottou, Y. Bengio, and P. Haffner, "Gradient-Based Learning Applied to Document Recognition," Proceedings of the IEEE, vol. 86, no. 11, pp. 2278-2324, 1998, doi: 10.1109/5.726791.
S. Hochreiter and J. Schmidhuber, "Long Short-Term Memory," Neural Computation, vol. 9, no. 8, pp. 1735-1780, 1997.
A. Apichottanakul, K. Piewthongngam, and S. Pathumnakul, "Using an Artificial Neural Network to Forecast the Market Share of Thai Rice," in 2009 IEEE International Conference on Industrial Engineering and Engineering Management, 2009: IEEE, pp. 665-668.
H. Hruschka, "Determining Market Response Functions by Neural Network Modeling: A Comparison to Econometric Techniques," European Journal of Operational Research, vol. 66, no. 1, pp. 27-35, 1993.
D. Agrawal and C. Schorling, "Market Share Forecasting: An Empirical Comparison of Artificial Neural Networks and Multinomial Logit Model," (in English), Journal of Retailing, Article vol. 72, no. 4, pp. 383-407, Win 1996, doi: 10.1016/s0022-4359(96)90020-2.
K. E. Fish, J. D. Johnson, R. E. Dorsey, and J. G. Blodgett, "Using an Artificial Neural Network Trained with a Genetic Algorithm to Model Brand Share," Journal of Business Research, vol. 57, no. 1, pp. 79-85, 2004.
F. Yang, "A Research on Deep Neural Network Based Airline Market Share Prediction Model in Aviation Market Network Evaluation," in 2018 IEEE 4th International Conference on Computer and Communications (ICCC), 7-10 Dec. 2018 2018, pp. 2158-2162, doi: 10.1109/CompComm.2018.8780832.
B. Szkuta, L. A. Sanabria, and T. S. Dillon, "Electricity Price Short-Term Forecasting Using Artificial Neural Networks," IEEE Transactions on Power Systems, vol. 14, no. 3, pp. 851-857, 1999.
M. M. Cai, M. Pipattanasomporn, and S. Rahman, "Day-Ahead Building-Level Load Forecasts Using Deep Learning Vs. Traditional Time-Series Techniques," (in English), Applied Energy, Article vol. 236, pp. 1078-1088, Feb 2019, doi: 10.1016/j.apenergy.2018.12.042.
T. Kaya, E. Aktas, İ. Topçu, and B. Ülengin, "Modeling Toothpaste Brand Choice: An Empirical Comparison of Artificial Neural Networks and Multinomial Probit Model," International Journal of Computational Intelligence Systems, vol. 3, no. 5, pp. 674-687, 2010.
G. Taguchi, "Introduction to Quality Engineering: Designing Quality into Products and Processes," 1986.
李輝煌, 田口方法-品質設計的原理與實務. 高立圖書有限公司, 2004.
T.-Y. Wang and C.-Y. Huang, "Improving Forecasting Performance by Employing the Taguchi Method," European Journal of Operational Research, vol. 176, no. 2, pp. 1052-1065, 2007.
R. J. Hodrick and E. C. Prescott, "Postwar Us Business Cycles: An Empirical Investigation," Journal of Money, Credit, and Banking, pp. 1-16, 1997.
J. F. Khaw, B. Lim, and L. E. Lim, "Optimal Design of Neural Networks Using the Taguchi Method," Neurocomputing, vol. 7, no. 3, pp. 225-245, 1995.