Using the sea surface temperature (SST) hindcast datasets produced by the climate system model of Beijing Climate Center (BCC_CSM1.1m) from 1991 to 2014, the Stepwise Pattern Projection Method (SPPM) is employed to statistically correct El Ni〖AKn~D〗oSouth Oscillation (ENSO) prediction. The main idea of the SPPM is to produce a prediction at the predictand grid by projecting the predictor field onto its covariance pattern with the onepoint predictand after selecting the predictor domain. The SPPM significantly improves the performance of the prediction over the equatorial Pacific and Indian Ocean. The temporal correlation score has increased 8%-10% in terms of Ni〖AKn~D〗o3.4 SST anomaly index with a 6month lead in the cross validation. The spatial anomaly correlation coefficients for El Ni〖AKn~D〗o event predictions also increase obviously by the SPPM at most lead months, particularly in autumn. Besides, the prediction for the location of warming center also can be improved, compared with that of the original BCC_CSM1.1m.