Computed tomography (CT) perfusion imaging is a routinely used technique in the field of neurovascular imaging. The progression of a bolus of contrast agent through the neurovasculature is imaged in a series of CT scans. Relevant perfusion parameters, such as cerebral blood volume (CBV) and flow (CBF), can be computed by the deconvolution of the contrast-time curves with the bolus shape measured at one of the feeding arteries. These parameters are crucial in the treatment of acute stroke, where they can identify the portions of likely salvageable tissue and irreversibly damaged infarct core. Deconvolution is normally achieved using singular value decomposition (SVD). However, studies have shown that these algorithms are noise sensitive and easily influenced by artifacts in the source image, and subsequently may introduce further distortions that negatively influence the estimated output parameters. In this study, we present a machine learning approach to the estimation of perfusion parameters from CT imaging. Standard types of regression-based machine learning models were trained on the raw CT perfusion imaging data to reproduce the output of an FDA approved commercial implementation of the SVD deconvolution algorithm. Experiments were conducted to evaluate the performance of various regression-based machine learning models. Among the models evaluated, kernel ridge regression and random forest models performed best (SSIM: $~82\%, ~84\%$), trading off quick run time for better prediction accuracy while requiring a low number of training examples.