Background: Lenvatinib plus PD-1 inhibitors and interventional (LPI) therapy has demonstrated promising treatment effects in unresectable hepatocellular carcinoma (uHCC). However, biomarkers for predicting the response to LPI therapy remained to be further explored. The current study aimed to develop a radiomics model to noninvasively predict the efficacy of LPI therapy for uHCC. Methods: Clinical data of patients who were diagnosed with uHCC and accepted LPI therapy were collected in our institution. The clinical model was built by clinicopathological information. Nine machine learning classifiers were tested and the multilayer perceptron classifier with optimal performance was utilized as the radiomics model. The clinical-radiomics model was constructed by integrating clinical and radiomics scores. Results: 151 patients were enrolled in this study (2:1 randomization, 101 and 50 in the training and validation cohorts), of which three patients achieved complete response, 69 showed partial response, 46 showed stable disease and 33 showed progressive disease (evaluated by mRECIST criteria). The objective response rate (ORR), disease control rate (DCR), and conversion resection rate were 47.7, 78.1 and 23.2%, respectively. 14 features were selected from the initially extracted 1223 for radiomics model construction. The area under the curves of the radiomics model (0.900 for training and 0.893 for validation) were comparable to that of the clinical-radiomics model (0.912 for training and 0.892 for validation), and both were superior to the clinical model (0.669 for training and 0.585 for validation). Meanwhile, the radiomics model could categorize participants into high- and low-risk groups for progression-free survival and overall survival in the training and validation sets. Conclusions: The current study developed a novel and promising machine learning radiomics model, which could efficiently predict the efficacy of LPI therapy for uHCC, with comparable performance to clinical-radiomics model.