The Interest in Implementing Self-Consolidating Concrete (SCC) in Major Construction Projects Has Increased Significantly in Recent Years. This Paper Reports the Results of an Extensive Survey of Experimental Data of More Than 1700 SCC Mixtures from over 100 Studies Published in the Last Decade. the Survey Included the SCC Mixture Proportioning, Key Fresh Properties Including Flowability, Passing Ability, and Segregation Resistance, as Well as Some of the Derived Properties (E.g., Paste Volume). the Statistical Analysis of the Reported Parameters Showed Wide Variations in Values. the Outcome of the Survey Indicates that SCC Mixture Design and Workability Properties Do Not Systematically Lie within the Recommendations Reported in Various Guidelines. a Wide Range of Workability Tests is Used; However, only 22 % of the Studies Reported Values for Segregation Resistance. the Slump Flow Test Was the Most Tested Fresh Property and the Most Reported Values Are in Range of 591–760 Mm (X¯ = 679 Mm). the V-Funnel Time Was the Second Most Reported Test, and the Most of Reported Values Are in Range of 4.0–20 S (X¯ = 11 S). the Study Devised and Evaluated the Efficacy of using Machine Learning (ML) Models, Namely Extreme Gradient Boosting (XGBoost), to Predict the Two Most Reported Workability Characteristics of SCC, Namely Slump Flow and V-Funnel Flow Time. the Model Was Formulated to Predict Slump Flow and V-Funnel Time using a Refined Sub-Database of 852 Tests (The Extreme Data I.e., 5 % from Each Side, for the Both Properties and the Empty Data Was Deleted). the Findings Revealed that the XGBoost Model Can Provide an Accurate Prediction for the Slump Flow and V-Funnel Values, Thus Indicating its Potential as a Powerful Tool for SCC Optimization. the Findings Provide Valuable Insights into the Application of ML in SCC Research and Contribute to the Development of More Efficient and Sustainable Construction Practices.