Understanding the load-carrying capacity of circular concrete-filled steel tube (CCFST) columns is crucial for designing CCFST structures. However, traditional empirical formulas often yield inconsistent results for the same scenario, causing confusion for decision makers. Additionally, simple regression analysis is unable to accurately predict the complex mapping relationship between input and output variables. To address these limitations, this paper proposes an ensemble model that incorporates multiple input features, such as component geometry and material properties, to predict CCFST load capacity. The model is trained and tested on two datasets comprising 1305 tests on CCFST columns under concentric loading and 499 tests under eccentric loading. The results demonstrate that the proposed ensemble model outperforms conventional support vector regression and random forest models in terms of the determination coefficient (R2) and error metrics (MAE, RMSE, and MAPE). Moreover, a feature analysis based on the Shapley additive interpretation (SHAP) technique indicates that column diameter is the most critical factor affecting compressive strength. Other important factors include tube thickness, yield strength of steel tube, and concrete compressive strength, all of which have a positive effect on load capacity. Conversely, an increase in column length or eccentricity leads to a decrease in load capacity. These findings can provide useful insights and guidance for the design of CCFST columns.