Reciprocating seal located directly on the rod/piston of a reciprocating equipment is used for preventing leakage and reducing wear between two parts that are in relative motion. Degradation assessment of reciprocating seal is extremely important in the manufacturing industry to avoid fatal breakdown of reciprocating equipment and machines. In this paper, we have proposed a data-driven prognostics approach using friction force to predict the degradation of reciprocating seal using Support Vector Regression. Statistical time domain features are extracted from friction force signal to reduce the complexity of raw data. Principal Component Analysis is used to fuse the relevant features and remove the redundant features from the process. Based on the selected features, a Support Vector Regression model is then built and trained for the prediction of seal degradation. A Grid search method is used to tune the hyperparameters in the SVR model. Run-to-failure data collected from an experimental test set-up is used to validate the proposed methodology. The study findings indicate that a small set of relevant features which can represent the pattern related to degradation is sufficient to have a high prediction accuracy. The seal tested for this study comes from oil and gas industry, but the proposed method can be implemented in any industry with reciprocating equipment and machines.