BACKGROUND: The risk of liver metastasis (LM) may be estimated using predictive nomograms. While the nomogram has recently been applied in oncology, there are relatively few studies concentrating on predicting LM in patients with early-onset colon cancer. We aimed to identify independent risk factors for LM in patients with early-onset colon cancer and develop a nomogram for predicting the probability of LM in these patients. METHODS: Our study encompassed 4,890 early-onset colon cancer patients with LM who were registered in the Surveillance, Epidemiology, and End Results (SEER) database from 2010 to 2015. These patients were randomly allocated into training and validation cohorts at a ratio of 7:3. Univariate and multivariate logistic regression analyses were conducted to identify the independent risk factors for LM, and a nomogram was developed using these factors. The model's discriminatory power, accuracy, and clinical utility were evaluated using receiver operating characteristics (ROC), calibration, and decision curve analyses. RESULTS: Overall, 4,890 patients with early-onset colon cancer and LM were selected from the SEER database. LM incidence in these patients was 18.4%. Univariate and multivariate analyses revealed histological type, T stage, N stage, and carcinoembryonic antigen (CEA) level as independent risk factors. ROC curve analysis revealed that the predictive nomogram for LM risk had an area under the curve of 0.812 [95% confidence interval (CI): 0.795-0.829] and 0.809 (95% CI: 0.784-0.834) in the training and validation sets, respectively, demonstrating good discriminatory ability of the model. Calibration curve analysis showed good agreement between predicted values from the nomogram and actual observations, and the decision curve analysis (DCA) demonstrated the high clinical utility of the nomogram. CONCLUSIONS: LM incidence was higher in patients with early-onset colon cancer. Our nomogram demonstrates a high level of efficacy in predicting the risk of LM in patients with early-onset colon cancer, thereby assisting clinicians in making well-informed treatment decisions prior to further intervention.