High service availability and reliability with low failure occurrence probability are requirements for a large-scale cloud data center. Despite this, large-scale cloud data centers nevertheless experience high failure rates due to a variety of factors, including hardware and software faults, which frequently lead to task and job failures. Such failures can significantly lower cloud service reliability and need a significant number of resources to recover. Therefore, it's crucial to accurately estimate tasks or job failures in advance to prevent unforeseen wastage. By examining historical system message logs and establishing a link between the data and failures, numerous machine learning and deep learning-based algorithms for task or job failure prediction have been presented. In this, a failure prediction algorithm called Voting Classifier is proposed to identify task and job failures in the cloud, further increasing the failure prediction accuracy of the prior machine learning and deep learning-based methods. To determine whether tasks and occupations will be successful or unsuccessful is the aim of the Voting Classifier failure prediction algorithm.