The quantitative structure–property relationship (QSPR) models of the inhibition efficiency of seventeen α-amino acids for copper in acidic medium to their calculated reactivity indicators were developed. DFT calculations and Monte Carlo simulations were employed to find out these indicators. Both multi-linear regression (MLR) and artificial neural network (ANN) methods were employed. The most relevant global descriptors were selected using the simulated annealing algorithm. The QSPR studies showed that the inhibiting performance of the investigated compounds was influenced by their electronegativity, LUMO energy, fraction of electron transferred and total negative charge. The results show that the ANN based model exhibits a great predictive performance compared with MLR model according to correlation coefficient and the root-mean-squared error. In addition, this indicates that the corrosion inhibition of copper by these α-amino acids is mainly a complex phenomenon. Moreover, by analysis of local reactivity indicators and using the ANN constructed model, ten new designed derivative compounds with their predicted inhibition efficiency were proposed. Keywords: Corrosion, Modeling, DFT, Monte Carlo, Simulated annealing, QSPR