We propose the new parallel algorithm of local support vector regression (local SVR), called $k$SVR for effectively dealing with large datasets. The learning strategy of $k$SVR performs the regression task with two main steps. The first one is to partition the training data into $k$ clusters, followed which the second one is to learn the SVR model from each cluster to predict the data locally in the parallel way on multi-core computers. The $k$SVR algorithm is faster than the standard SVR for the non-linear regression of large datasets while maintaining the high correctness in the prediction. The numerical test results on datasets from UCI repository showed that our proposed $k$SVR is efficient compared to the standard SVR.