Demand forecasting based machine learning algorithms on customer information: an applied approach

Demand forecasting has always been a concern for business owners as one of the main activities in supply chain management. Unlike the past, that forecasting was done with the help of a limited amount of information, today, using advanced technologies and data analytics, forecasting is performed with machine learning algorithms and data-driven methods. Patterns and trends of demand, customer information, preferences, suggestions, and post-consumption feedbacks are some types of data that are used in various demand forecasting efforts. Traditional statistical methods and techniques are biased in demand prediction and are not accurate; so, machine learning algorithms as more popular techniques have been replaced in recent researches in the literature. Until the time of conducting this research, extreme learning machine has not been used for intermittent demand prediction, so the novelty of our research is to adopt this algorithm and also other machine learning algorithms such as K-nearest neighbors, decision tree, gradient boosting, and multi-layer perceptron to examine its accuracy and performance in comparison to other approaches. Finally, it is demonstrated that artificial neural network-based methods outperform the other employed techniques through conducting a comparison among the above-mentioned predictors in terms of mean squared error, mean absolute error, coefficient of determination, and computational time. Furthermore, extreme learning machine is the best or at least among the best predictors. At last, for determining whether the obtained results are statistically significant or not, analysis of variance is conducted and the Kolmogorov–Smirnov technique is adopted to test the normality of outcomes.