• Ashish Oberoi

Full supply chain collaboration is a goal that the participating companies should strive towards new business. However, a number of obstacles stand in the way of true progress in this area. As a result, in the lack of complete information about other participants' desire, participants must predict their own demand. We look at how sophisticated machine learning techniques like neural networks, recurrent neural networks, and support vector machines may be used to anticipate skewed demand at the end of a supply chain in this article (bullwhip effect). These approaches are compared to more classic methods such as naive forecasting, trend, moving average, and linear regression. For our studies, we employ two data sets: one from a simulated supply chain, and another from genuine Canadian Foundries orders. Our findings imply that while recurrent neural networks and support vector machines outperform the regression model in terms of predicting accuracy, they are not statistically substantially superior.

Image Processing, Machine Learning, Neural Networks, Product, Supply Chain.

"Application of Machine Learning For Supply Chain", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.5, Issue 9, page no.318-323, September 2018, Available :http://www.jetir.org/papers/JETIRFH06054.pdf

"Application of Machine Learning For Supply Chain", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.5, Issue 9, page no. pp318-323, September 2018, Available at : http://www.jetir.org/papers/JETIRFH06054.pdf