<p>Chemical composition in cutting fluids predominantly influences the performance of various metal-cutting operations, the health of the worker and the nearby environment. The application of environmentally friendly fluids in the minimum quantity lubrication (MQL) technique can reduce such adverse effects in cutting operations through their extensive properties. Optimizing the process parameters in MQL cooling techniques is essential to solving the low-efficiency problem associated with environmentally friendly fluids. The current research is aimed to optimise the machining parameters with multi-response outcomes in turning by designing the experiments in Taguchi’s L₂₇ orthogonal array. Grey relational analysis (GRA) was integrated with Taguchi methods to achieve simultaneous optimization of cutting force and surface roughness.&#xa0;The process parameters such as nozzle angle, pressure and fluid flow rate are considered to study their behavior in turning SS304 alloy. The ‘Smaller-is-better’ strategy is followed to find the ideal combination of parameters from Taguchi’s signal-to-noise ratio graphs. The performance index is evaluated through grey relational grading (GRG) system and optimality is achieved at a nozzle angle of 60°, a pressure of 6&#xa0;bar and a flow rate of 20&#xa0;mL/min. The prediction of surface roughness and cutting force has been carried out using ANN with optimal network structure of 3-4-2. The optimized model achieved an R² value of 0.99 for both training and testing. An artificial neural network (ANN) with a 3-4-2 architecture was used to predict surface roughness and cutting force, yielding an R² value of 0.99 for both training and testing datasets. Notably, the fluid flow rate emerged as the significant factor (89% influence), outperforming pressure (4%) and nozzle angle (7%), highlighting its important role in effective lubrication during machining.</p> Graphical abstract <p></p>