IJSTR

International Journal of Scientific & Technology Research

Home About Us Scope Editorial Board Blog/Latest News Contact Us
0.2
2019CiteScore
 
10th percentile
Powered by  Scopus
Scopus coverage:
Nov 2018 to May 2020

CALL FOR PAPERS
AUTHORS
DOWNLOADS
CONTACT

IJSTR >> Volume 9 - Issue 6, June 2020 Edition



International Journal of Scientific & Technology Research  
International Journal of Scientific & Technology Research

Website: http://www.ijstr.org

ISSN 2277-8616



Time Series Forecast For Non-Linear Sales Trend

[Full Text]

 

AUTHOR(S)

Yousef Humsi, Dr. Waleed Al-Sitt

 

KEYWORDS

LTSM, Normalizing, ML, One-hot encode, Outliers

 

ABSTRACT

Sales forecast is an essential tool for any company seeking success, as it gives insight into how a company should manage its workforce, income and resources. Additionally, sales forecast help companies to allocate their internal assets viably. In this paper will report two different approaches for forecasting non-linear sales trends using Long Short-Term Memory (LTSM) and Facebook developed model (Prophet) by implementing it on multiple sources of historical sales data.

 

REFERENCES

[1] Navratil, Miroslav & Kolková, Andrea. (2019). Decomposition and Forecasting Time Series in Business Economy Using Prophet Forecasting Model. Central European Business Review. 8. 26-39. 10.18267/j.cebr.221.
[2] Hua, Yuxiu & Zhifeng, Zhao & Li, Rongpeng & Chen, Xianfu & Liu, Zhiming & Zhang, Honggang. (2019). Deep Learning with Long Short-Term Memory for Time Series Prediction. IEEE Communications Magazine. PP. 1-6. 10.1109/MCOM.2019.1800155.
[3] Pavlyshenko, Bohdan. (2019). Machine-Learning Models for Sales Time Series Forecasting. Data. 4. 15. 10.3390/data4010015.
[4] Miao, Jianyu & Niu, Lingfeng. (2016). A Survey on Feature Selection. Procedia Computer Science. 91. 919-926. 10.1016/j.procs.2016.07.111.
[5] Pearson, Ronald & Neuvo, Y. & Astola, J. & Gabbouj, Moncef. (2015). The class of generalized hampel filters. 2501-2505. 10.1109/EUSIPCO.2015.7362835.
[6] Alon, Ilan & Qi, Min & Sadowski, Robert. (2001). Forecasting aggregate retail sales: A comparison of artificial neural networks and traditional methods. Journal of Retailing and Consumer Services. 8. 147-156. 10.1016/S0969-6989(00)00011-4.