This paper explores the integration of Machine Learning (ML) into the Open Radio Access Networks (O-RAN) architecture to optimize dynamic resource allocation. The authors propose an xApp-based implementation of an ML algorithm to dynamically adjust the allocation of Physical Resource Blocks (PRBs) based on traffic demand and Quality of Service (QoS) requirements. The core aim is to optimize resource allocation and meet Service Level Specifications (SLS). The proposed ML model, specifically the Random Forest Classifier, achieves high performance accuracy (85%) in selecting the best allocation policy for each base station, enhancing the scheduler functionality in the O-RAN Distributed Unit (O-DU). The study demonstrates that the ML-based approach effectively manages network resources, improves network performance, and ensures high-quality service delivery. The integration of AI and ML within O-RAN not only enhances network optimization but also enables intelligent decision-making and automated operations, contributing to more resilient and adaptable telecommunication networks.This paper explores the integration of Machine Learning (ML) into the Open Radio Access Networks (O-RAN) architecture to optimize dynamic resource allocation. The authors propose an xApp-based implementation of an ML algorithm to dynamically adjust the allocation of Physical Resource Blocks (PRBs) based on traffic demand and Quality of Service (QoS) requirements. The core aim is to optimize resource allocation and meet Service Level Specifications (SLS). The proposed ML model, specifically the Random Forest Classifier, achieves high performance accuracy (85%) in selecting the best allocation policy for each base station, enhancing the scheduler functionality in the O-RAN Distributed Unit (O-DU). The study demonstrates that the ML-based approach effectively manages network resources, improves network performance, and ensures high-quality service delivery. The integration of AI and ML within O-RAN not only enhances network optimization but also enables intelligent decision-making and automated operations, contributing to more resilient and adaptable telecommunication networks.