<p>To create lightweight structures with excellent mechanical performance and economic effectiveness in aerospace production, the best materials must be chosen. Aluminium alloys are favoured because of their superior workability, corrosion resistance, and strength-to-weight ratio. However, there are other, frequently incompatible factors to consider when selecting the best alloy for a particular procedure, like cold extrusion. In order to systematically assess and rank five Aluminium alloys called AA1100, AA2014, AA2024, AA6063 and AA7075 based on seven mechanical attributes like tensile strength, thermal conductivity, coefficient of thermal expansion, modulus of elasticity, hardness, fracture strength, and melting temperature, this study incorporates a Multi-Criteria Decision-Making (MCDM) approach using the VIKOR method. To ensure an impartial assessment, each criterion is given an equal weight. According to the findings, the best material for cold extrusion applications in aerospace is AA2014. A Customized Automated Machine Learning (CAML) framework is also used in the study to support material selection with predictive process modeling. Key extrusion responses, including force, displacement, extrusion time, and compressive strength, are predicted using machine learning models based on experimental data. The CAML frame work structured clearly to illustrate the data preprocessing, model selection, hyper parameter tuning, and evaluation steps for reproducibility. Cross-validation and hyper parameter alteration are used to refine the CAML framework, which used evaluation measures (R2, RMSE, and MAE) to assure optimal model selection. The combination of the VIKOR technique and CAML offers a complete decision-support system that improves efficiency and reliability in the design and manufacture of aerospace components by accurately predicting process outcomes in addition to identifying the optimal material.</p> Graphical abstract <p></p>