INTRODUCTION: Transjugular intrahepatic portosystemic shunt (TIPS) relieves portal hypertension, but post-TIPS overt hepatic encephalopathy (OHE) and variceal rebleeding (VRB) remain outcomes that significantly impair survival. The aim of this study was to identify risk factors and develop an interpretable machine learning model predicting 2-year and 6-year OHE and VRB. METHODS: In this multicenter retrospective study, 636 patients undergoing TIPS (2014–2023) with 2–6 years follow-up were analyzed. A detailed perioperative data set was curated. Least Absolute Shrinkage and Selection Operator selected key predictors for model training in an integrated machine learning voting ensemble (ML-VE) framework. Efficacy was assessed by area under the receiver operating characteristic curve (AUC) and compared with conventional clinical scores (Child-Pugh, MELD, and MELD-Na). Subgroup analyses were conducted, and Shapley Additive Explanations were used for interpretation. RESULTS: The cumulative incidences of OHE and VRB were 22.2% and 8.2% at 2 years, respectively, increasing to 24.8% and 10.1% at 6 years. Internally, ML-VE achieved AUCs of 0.960 (OHE) and 0.966 (VRB) at 2 years and 0.849 (OHE) and 0.828 (VRB) at 6 years. External validation for OHE yielded AUCs of 0.914 at 2 years and 0.924 at 6 years, outperforming conventional scores (AUC 0.528–0.563 for OHE; 0.528–0.555 for VRB). All prespecified subgroups had 2-year AUCs ≥0.93 (OHE prediction in portal vein thrombosis: 0.993; VRB prediction in portal pressure gradient 9–12 mm Hg: 0.987). SHapley Additive exPlanationsidentified “diabetes” as the strongest predictor of OHE and “recent bleeding” as the strongest predictor of VRB at 2 years. DISCUSSION: The interpretable ML-VE model showed good discrimination for 2-year and 6-year post-TIPS OHE and VRB risk, suggesting potential utility for short-term and long-term risk stratification after TIPS.