In this study, a novel computational prediction tool, abbreviated as predCitru-Site , has been developed to predict citrullination site. This technique effectively incorporates sequence coupling effect of surrounding amino acids of arginine residues for decision making using a supervised support vector machine (SVM) algorithm. With the assistance of Different Error Costs (DEC) method, SVM successfully made wise decision by balancing the negative effect of skewed training citrullination dataset. The performance of predCitru-Site was measured from the average of 5 complete runs of the 10-fold cross-validation test to comply with existing tools. predCitru-Site achieved 97.6% sensitivity, 98.9% specificity, and overall accuracy of 98.5%. With a 0.967 Matthew’s correlation coefficient, it has showed an area under the receiver operator characteristics curve of 0.997. Compared with existing tools, predCitru-Site significantly outperforms the same test dataset. These results suggest that our method is promising and can be used as a complementary technique for fast exploration of citrullination in arginine residue. A user-friendly web server has also been deployed at http://research.ru.ac.bd/predCitru-Site/ for the convenience of experimental scientist.