本研究的目的是以A公司為例，分析電子連接器的銷售回報和收入預測。這些數據被視為時間序列的數據。因此，統計分析可以揭示可能的趨勢，並且可以預測A公司的收入。因此，管理者可以針對不斷變化的市場迅速做出相關決策，使公司的運營進入正確的軌道並繼續增長。對銷售和退貨數據的統計分析表明，A公司的主要銷售集中在幾個產品類別上，退貨產品的情況也是如此。銷售額的下降與其客戶的季節性備貨和購買策略有關。這種趨勢不是固定的，而是每一季都有變化。

對於A公司來說，Prophet對2021年的收入預測比實際銷售小2.3% 左右。該預測對於管理者採取及時的行動來說是合理準確的。也就是說，當有適當的數據庫可供訓練時，Prophet工具可用於銷售預測。

The purpose of this study is to analyze the sales return and revenue forecast of electronic connectors, using Company A as an example. The data were treated as time series ones. Thus, statistical analysis can reveal possible trends and revenue can be predicted for Company A. Therefore, managers can make relevant decision for the changing market quickly to put the operation of the company onto the right track and continue its growth.

The statistical analysis of the sales and sales return data indicates that the main sales of Company A are concentrated in a few product categories, and the same is true for returned products. The decline of the sales is related to the seasonal stocking and buying strategies its customers. This trend is not fixed but varies from season to season.

For Company A, the revenue forecast predicted for 2021 by Prophet is about 2.3% smaller than the actual sales. The prediction is reasonably accurate for managers to take timely actions. That is, the Prophet tool can be used for sales prediction when proper database are available for training.

[1] 張云濤,龔玲.資料探勘原理與技術二版 (2nd ed).五南圖書.(2019).
[2] 王實,高文,&李錦濤.Web數據探勘 (Vol. 27). 電腦科學.(2000).
[3] 王進德.類神經網路與模糊控制理論入門與應用. 全華圖書.(2007).
[4] 黃國源.類神經網路.全華圖書.(2015).
[5] 谷岡広樹, & 康鑫. 深度學習入門教室：6堂基礎課程+Python實作練習，Deep Learning、人工智慧、機器學習的理論和應用全圖解. 臉譜.(2019).
[6] 李玉華.應用時間序列與類神經網路技術於銷售預測模型之研究.(2015).
[7] 余桂霖.時間序列分析. 台灣五南圖書出版股份有限公司.(2013).
[8] 楊勝凱.運用類神經網路與時間序列分析建構台灣 50 股價預測模型. (2011).
[9] 陳旭昇.時間序列分析:總體經濟與財務金融之應用. 臺灣東華.(2013).
[10] Snow, D. (2020). AtsPy: Automated Time Series Forecasting in Python. Available at SSRN 3580631.
[11] Adiga, R. (2022). Prophet Model Using Belgium Dataset. Science, 1(01), 36-41.
[12] Oo, Z. Z., &Sabai, P. H. Y. U. (2020). Time Series Prediction Based on Facebook Prophet: A Case Study, Temperature Forecasting in Myintkyina. International Journal of Applied Mathematics Electronics and Computers, 8(4), 263-267.
[13] Jha, B. K., & Pande, S. (2021, April). Time series forecasting model for supermarket sales using FB-prophet. In 2021 5th International Conference on Computing Methodologies and Communication (ICCMC) (pp. 547-554). IEEE.
[14] Brownlee ,jason. (2020, August 6). Time Series Forecasting With Prophet in Python. Retrieved from https://machinelearningmastery.com/time-series-forecasting-with-prophet-in-python/
[15] Sean J. Taylor,& Ben Letham. (2017, February 23). Prophet：大規模預測. Retrieved from https://research.facebook.com/blog/2017/2/prophet-forecasting-at-scale/
[16] Jha, B. K., & Pande, S. (2021, June 6). Time Series Forecasting Model for Supermarket Sales Using FB-Prophet. Retrieved from https://ieeexplore.ieee.org/abstract/document/9418033/authors#authors
[17] Park, J. C., Chang, B. P., &Mok, N. (2019). 144 Time Series Analysis and Forecasting Daily Emergency Department Visits Utilizing Facebook's Prophet Method. Annals of Emergency Medicine, 74(4), S57.
[18] Li, Y., Yang, Y., Zhu, K., & Zhang, J. (2021). Clothing Sale Forecasting by a Composite GRU–Prophet Model With an Attention Mechanism. IEEE Transactions on Industrial Informatics, 17(12),8335-8344.
[19] Yusof, U. K., Khalid, M. N. A., Hussain, A., &Shamsudin, H. (2020, December). Financial Time Series Forecasting Using Prophet. In International Conference of Reliable Information and Communication Technology, pp. 485-495 Springer, Cham.
[20] Ying, Z. H. A. O., Yuan-wei, Z. H. A. I., Jun-jun, C. H. E. N., & Jian, T. E. N. G. (2020). Time Series Forecasting Model Based on LSTM-Prophet Nonlinear Combination. Computer And Modernization, (09), 6.
[21] Weytjens, H., Lohmann, E., &Kleinsteuber, M. (2021). Cash flow prediction: MLP and LSTM compared to ARIMA and Prophet. Electronic Commerce Research, 21(2), 371-391.
[22] Mahanty, M., Swathi, K., Teja, K. S., Kumar, P. H., &Sravani, A. (2021). Forecasting the Spread of COVID-19 Pandemic with Prophet. Rev. d'IntelligenceArtif., 35(2), 115-122.
[23] Yoo, T. W., & Oh, I. S. (2020). Time series forecasting of agricultural products’ sales volumes based on seasonal long short-term memory. Applied Sciences, 10(22), 8169.
[24] Alshara, M. A. (2022). Stock Forecasting Using Prophet vs. LSTM Model Applying Time-Series Prediction. IJCSNS, 22(2), 185.