The shear resistance of cold joint in concrete is influenced by various design parameters. Traditional mechanical models typically consider only a limited number of parameters to predict the shear strength of cold joints. This research aims to explore the complex nonlinear relationship between design parameters and cold joint shear strength using statistical method and machine learning technology. The goal is to develop a more accurate, reliable, and engineering applicable regression model for predicting shear strength. A dataset of 546 Z-shaped shear specimens characterizing cold joint in concrete was constructed, involving a total of 16 variables that may affect shear performance. Correlation analysis and recursive elimination were adopted to eliminate correlated and insignificant variables based on their importance. Multiple linear regression (MLR), random forest regression (RFR), and support vector machine regression (SVR) prediction models for cold joint shear strength were established based on rigorously screened variables and comprehensively evaluated using multiple methods. It was found that the most significant factors influencing the shear strength of cold joints are concrete strength, interface shear key, product of interface reinforcement strength and its reinforcement ratio, normal stress, fiber length of new concrete, casting method of the new concrete, and product of the fiber length and its tensile strength of old concrete. The MLR, SVR, and RFR models all exhibited superior performance relative to traditional mechanics-based models with regard to shear strength prediction of cold joints. The RFR model is recommended for predicting the shear strength of cold joints due to its superior evaluation indexes in comparison to the MLR and SVR models, and variable sensitivity analysis shows that it does not yield common-sense errors.