Machine Learning For Intermittent Demand Forecasting
Intermittent, demand forecasting, Croston’s method, artificial neural networks, support vector machines
Forecasting demand is a crucial step in inventory control; its accuracy affects the management of storage and materials, and therefore the profitability of the company. When the demand is intermittent, infrequent, and highly variable when it occurs, it causes problems when using traditional statistical models and forecasting techniques (constant forecasts, zero forecasts, unsuitable accuracy metrics, etc). This work is a comparison between several methods, including the Croston's method specific for intermittent demand, and other important machine learning techniques such as artificial neural networks, using a database of different spare part products. Our objective is to forecast the demand of these products in the most accurate way possible, and to apply methods that can outperform the conventional methods.
"Machine Learning For Intermittent Demand Forecasting", IJSDR - International Journal of Scientific Development and Research (www.IJSDR.org), ISSN:2455-2631, Vol.2, Issue 1, page no.99 - 102, January-2017, Available :https://ijsdr.org/papers/IJSDR1701017.pdf
Volume 2
Issue 1,
January-2017
Pages : 99 - 102
Paper Reg. ID: IJSDR_170019
Published Paper Id: IJSDR1701017
Downloads: 000347079
Research Area: Applied Mathematics
Country: Hadath, Lebanon , Lebanon
ISSN: 2455-2631 | IMPACT FACTOR: 9.15 Calculated By Google Scholar | ESTD YEAR: 2016
An International Scholarly Open Access Journal, Peer-Reviewed, Refereed Journal Impact Factor 9.15 Calculate by Google Scholar and Semantic Scholar | AI-Powered Research Tool, Multidisciplinary, Monthly, Multilanguage Journal Indexing in All Major Database & Metadata, Citation Generator
Publisher: IJSDR(IJ Publication) Janvi Wave
