Bending is a commonly utilized method in the manufacturing of aluminum components. Spring back is a well-known problem in sheet metal forming that reduces operating efficiency and compromises dimensional precision. The Predicting the part's ultimate shape after spring back and designing tooling to adjust for it remains a practical concern in the manufacturing business. Using available finite element analysis (FEA) and Artificial Neural Network (ANN), this paper predicts the spring back of AA5052 under various variables. The results demonstrate that the spring back phenomenon is significantly influenced by the thickness of AA5052 and the angle of rolling. Following the thickness of AA5052, which accounts for 38.7% of the overall variance, angle of rolling, representing 32.3% of the total variation, is the procedure-dependent variable. The maximum spring back value was 10.5 at the thickest (2 mm) and the minimum was 3.5 at the thinnest 1 mm thickness in practice. The SB findings were analyses by comparing experimental, FEA, and ANN values. The ANN model exhibited a minimum SB of 3.488 with an error of 0.3%, whereas the FEA model demonstrated a minimum SB of 3.447 with an error of 1.56%. In this context, the ANN model is proficient in rapidly forecasting spring back, lowering analysis time, minimizing errors, lowering cost, and expediting product success.