The aims of the study were to build models using logistic regression analysis of flexibility and strength tests to prospectively predict risk factors for anterior cruciate ligament tear (ACL-tear) in female soccer (FS) players, and to determine training cut-off for risk factors of the predictive model built. A prospective cohort study of 95 female players (aged 14-33 years) was conducted. Age, anthropometric data, soccer history, lower limb range of motion (ROM) and hip maximal isometric strength (MIS) were measured. At the prospective follow-up after 12 months, 7.4% of the players had developed an ACL-tear. The model showed a significant relationship (χ 2 (93) = 30.531, p < 0.001) between the ACL-tear and the predictor variables (leg length, HAD-NH [hip adduction] MIS, asymmetric ROM [ankle dorsiflexion with knee extended (AD-KE) and with knee flexed (AD-KF), and HE (hip extension)], hip ROM [HIR (internal rotation) and HAB (abduction)]). The Akaike Information Criteria (AIC) and Bayesian Information Criteria (BIC) for model fit were 30.24 and 51.79, respectively. The value R 2 showed good model fit, 76.5% for Nagelkerke´s R 2 , 71.4% for McFadden´s R 2 and 67.5% for Tjur´s R 2 . For the screening test, cut-off for leg length of ≥0.40 m, for HIR ROM of ≤44º and for asymmetry of HE ROM of ≥5° were set, which have an acceptable (AUC ≥ 0.755) discriminatory ability for the development of ACL-tear.