Principal　component　analysis　(PCA)　is　employed　to　extract　the　principal　components　(PCs)　present　in　nuclear　mass　models　for　the　first　time.　The　effects　from　different　nuclear　mass　models　are　reintegrated　and　reorganized　in　the　extracted　PCs.　These　PCs　are　recombined　to　build　new　mass　models,　which　achieve　better　accuracy　than　the　original　theoretical　mass　models.　This　comparison　indicates　that　using　the　PCA　approach,　the　effects　contained　in　different　mass　models　can　be　collaborated　to　improve　nuclear　mass　predictions.