Machine Learning-Based Demand Forecasting in Supply Chains

Abstract

Effective supply chain management is one of the key determinants of success of today's businesses. However, communication patterns between participants that emerge in a supply chain tend to distort the original consumer's demand and create high levels of noise. In this article, we compare the performance of new machine learning (ML)-based forecasting techniques with the more traditional methods. To this end we used the data from a chocolate manufacturer, a toner cartridge manufacturer, as well as from the Statistics Canada manufacturing survey. A representative set of traditional and ML-based forecasting techniques have been applied to the demand data and the accuracy of the methods was compared. As a group, based on ranking, the average performance of the ML techniques does not outperform the traditional approaches. However, using a support vector machine (SVM) that is trained on multiple demand series has produced the most accurate forecasts.

Prediction of probable backorder scenarios in the supply chain using Distributed Random Forest and Gradient Boosting Machine learning techniques

“…Machine Learning (ML) techniques enable us to forecast accurately multiple aspects related to supply chain management such as demand, sale, revenue, production, and backorder. ML approaches have been used to predict manufacturers' garbled demands where some researchers applied a representative set of ML-based and traditional forecasting methods to the data to compare the precision of those used methods [19]. Those researchers found that the average performances of the ML method did not outperform the traditional methods, but when a Support Vector Machine (SVM) was trained on several demand-series, it produced the most precise predictions [20].…”

Role of Machine Learning in Manufacturing Sector

“…It is very important in the industry and includes storage of raw materials, inventory and includes all the processes which are needed to get the final product. Collaboration among the partners in a firm and sharing information is an important part in reducing demand errors but this approach is not always feasible as the full collaboration between stakeholders at all times is unfeasible [9]. Thus, supply chain forecasting is introduced to improve the savings.…”

“…Thus, supply chain forecasting is introduced to improve the savings. Some of the critical issues required that permit supply chain collaboration to be successful are listed below:  Business interests should be similar  Management of relationship in the long-term  Unwillingness to share information  The convoluted design and management of large-scale chains  The workers of supply chain should be competent [9] The machine learning algorithms can perform this forecasting better than humans as the system is very complex. Some of the traditional forecasting methods are listed below.…”

Expectation-Based Probabilistic Naive Approach for Forecasting Involving Optimized Parameter Estimation

“…Carbonneau et al [ 21 ] applied a representative set of traditional and ML-based forecasting techniques to the demand data and compared the accuracy of the methods. The average performance of the ML techniques did not outperform the traditional deterministic approaches.…”