Electrocardiogram (ECG) signals must be continuously recorded and monitored to effectively detect diseases caused by fast or slow heartbeat, that is, rhythm disorders. However, long monitoring periods generates large amount of data that are difficult to store and transmit. Moreover, these records may be subject to noise due to the environment. For this reason, there is a need for an ECG data compression algorithms that can produce effective results even in noisy environments. This study presents a new lossy method for ECG data compression based on the Support Vector Regression (SVR) technique. The SVR, a transform based method, allows the ECG data to be compressed in an optimal manner, since the accuracy is based on a provable algorithm. In transform based methods, it is very important to determine the number, shape, and location of the nonlinear basis functions that provide the transformation. The proposed method automatically determines the number, shape and location of these nonlinear basis functions, both optimally and quickly, thanks to the SVR optimization algorithm. Computer simulation results demonstrate the validity and feasibility of the proposed technique.