Supply chain digitalization correlates positively with organizations’ performance. To address the complexities and demands of digital supply chains (DSCs), create value, and remain competitive, supply chain stakeholders must develop and adopt new, specific digital and analytical capabilities and DSC management practices. Organizations are aiming to create more efficient, connected, and responsive supply chains through essential practices such as real-time data exchange, interoperability, and collaborative decision making. Based on these considerations and in response to recent calls to evaluate the use of machine learning (ML) models for forecasting, we investigated whether ML-based demand forecasting outperforms classical time-series forecasting methods such as autoregressive integrated moving average calculation, linear regression, and naïve forecasting. The core contribution of this chapter is to demonstrate the performance of ML models with structured datasets in the improvement of the operations management activity of forecasting.