Demand Forecasting Using Principal Component Analysis and Steepest Descent Based Regression Learning

Demand Forecasting Using Principal Component Analysis and Steepest Descent Based Regression Learning

Chitransh Popli¹, Prof. Priyanshu Dhameniya²

M.Tech Scholar (CSE)¹, Asst. Professor (CSE)²

AITR, Indore^1,2

ABSTRACT

Supply chain forecasting has seen a major inclination toward machine learning and evolutionary algorithms due to their capability to analyze large data sets. Sales forecasting is typically complex due to the volatility of the associated variables. This paper presents a machine learning based approach based on the principal component analysis (PCA) and the Scaled Conjugate Gradient (SCG) algorithm to for sales forecasting. The performance of the proposed system is evaluated in terms of the mean absolute percentage error (MAPE) and the regression. It is shown that the proposed system outperforms the previously existing system working on the benchmark datasets [1].

KEYWORDS

Supply chain forecasting, Regression Learning, Principal Component Analysis (PCA), Steepest Descent, Scaled Conjugate Gradient (SCG), Mean Absolute Percentage Error, Regression.