The invention belongs to the field of gene detection, and provides a gastric cancer peritoneal metastasis prediction gene model and its application, including PCLO, UGGT1, ZNF714, KIAA0825, COL23A1, MED1, NPAS2, TTC14, RPS27A, ASPH, ARHGEF12, SIK1, PAPPA, HHIPL1, MYO9B, ITPKB , ZNF862, MKNK1, MUC6, TRRAP, DUOX1, and KRTAP5‑2; the selected classifier SVM and the positive judgment threshold of 0.5 are effective and specific for predicting the risk of peritoneal metastasis. The application of the gene model of the present invention helps to predict the metastasis of gastric cancer patients, and is of great value and significance for timely taking effective clinical measures, formulating individualized diagnosis and treatment schemes, and finally improving the survival rate of gastric cancer patients.