Big data analysis using machine learning has become challenging problem to solve today. It become more challenging in classification problems when class distribution is imbalanced. In this paper we propose distributed ensemble model with intelligence technique based on Particle Swarm Optimization to overcome the imbalanced problem.For compensating the class imbalance first SMOTE is used to balance the minority class samples and then sampling based using Particle Swarm Optimization is applied. Here to perform fast processing whole model is implemented using spark-cluster computing which uses the underlying concept of parallel programming of spark RDD. Results of proposed system has shown the consistent improvements on several evaluation metrics and overall processing time. Evaluation of proposed system has been done using number of slaves in cluster,Precision,Recall and F-measure and also comparison between sequential and distributed ensemble model. Most of the existing techniques are showing different performance for different datasets, while proposed method has shown better generalization property which improves the data-model dependency issue. Proposed model has evaluate using KDD-CUP’99 intrusion detection and insect sensor dataset.For the datasets it shown better improvement over traditional sampling techniques.