Combining Smart Production Logistics (SPL) and Machine Learning (ML) for adaptive scheduling and execution of material handling may be critical for enhancing manufacturing competitiveness. SPL and ML may help identify, adapt, and respond to scheduling changes originating from disturbances in and enhance the operational performance of material handling. However, the literature combining SPL and ML for material handling is scarce. Accordingly, the purpose of this study is to propose a framework applying ML for the dynamic scheduling and execution of material handling tasks in SPL. The study proposes an architecture including Cyber Physical System (CPS) and Internet of Things (IoT) applying ML for the dynamic scheduling and execution of material handling. Then, we describe the ML inputs, interactions, and work flow for realizing the proposed architecture. Finally, the study presents digital services in a simulation environment exemplifying the dynamic scheduling and execution of material handling in SPL. The study concludes with essential implications to the manufacturing industry.