Predictive Model to Evaluate Achievement of the Sustainable Development Goals in Mexico Using an Artificial Neural Network

<ns3:p>Background Mexico’s commitment to the 2030 Agenda requires reliable forecasts of sustainability performance. Anticipating trends can help target interventions and allocate resources effectively. Methods An Artificial Neural Network (ANN) was trained on historical national time-series data to forecast three composite indicators through 2030: the Sustainable Development Index (SDI), the UN Sustainable Development Goals Index (ISDG), and the Economic Complexity Index (ECI). The model jointly learned patterns across indices to capture interdependencies relevant to sustainability outcomes. Results The ANN indicates interconnected dynamics among sustainability dimensions and suggests that measurable progress toward the SDGs by 2030 will depend on targeted policy effort in three domains: (1) education outcomes, (2) economic diversification that moves production toward higher-complexity activities, and (3) environmental strategies that mitigate ecological pressures. Forecasts underscore that gains in one area can reinforce others, but also that uneven advances may constrain aggregate progress. Conclusions Despite constraints—including a relatively short training series and omission of potentially important exogenous variables—the ANN provides a useful decision-support tool for refining sustainability policy. Future research should incorporate additional drivers (e.g., socio-economic, environmental, and governance covariates) and optimize ANN parameters to improve predictive accuracy and interpretability, helping ensure Mexico remains on track to meet its SDG commitments by 2030.</ns3:p>