Abstract Background: Microsurgical endodontic surgery is a standard tooth-preserving treatment. However, postoperative gingival recession, particularly in aesthetically critical areas, remains a common complication. A reliable tool for preoperative risk assessment is currently lacking. Objective: To identify key risk factors and develop an individualized nomogram for predicting gingival recession risk following microsurgical endodontics. Methods: This retrospective study analyzed 200 patients, including 50 with postoperative recession. Potential predictors were screened using Least Absolute Shrinkage and Selection Operator (LASSO) regression, and significant variables were incorporated into a multivariate logistic regression model to construct a nomogram. The model’s discrimination was assessed by the C-index, calibration was evaluated via calibration curves and the Hosmer-Lemeshow test, and internal validation was performed using 1,000 bootstrap resamples. Results: The study identified seven independent predictors: thin gingival biotype (OR=5.74), sulcular incision (OR=3.55), presence of restoration (OR=3.29), smoking (OR=2.96), and advanced age (OR=1.05). Conversely, greater keratinized gingiva width (OR=0.57) and the use of floss or water flosser (OR=0.35) were identified as protective factors. The final nomogram demonstrated excellent discrimination with a C-index of 0.87 (95% CI: 0.81; 0.92) and good calibration, supported by a Nagelkerke R2 of 0.46, a non-significant Hosmer-Lemeshow test (P=0.917), and high agreement in calibration curves (Mean Absolute Error=0.026). Conclusion: A validated nomogram integrating anatomical, surgical, and behavioral factors was developed. This tool facilitates preoperative identification of high-risk patients, enabling targeted preventive strategies to optimize aesthetic outcomes. Description of dataset and supplementary materials This package contains the raw data and supplementary materials necessary to replicate the findings of the study. Raw_Dataset.xlsx: The original dataset containing clinical parameters of the 200 patients analyzed in the study. Analysis_Code_R.docx: The R code scripts used for LASSO regression, multivariate logistic regression, and nomogram construction (provided in .docx format). Supplementary Table 1.docx: Verification of statistical assumptions for the final multivariate logistic regression model. Supplementary Table 2.docx: Internal validation of the final model using Bootstrap method (1,000 resamples).