Universities in Latin America commonly gather much more information about their students than allowed by data protection regulations in Western countries. We have tackled the question of whether the abundant data could be harnessed for the purpose of predicting academic outcomes and, thereby, taking proactive actions in student attention, course planning and resource management. A study was conducted to analyze the data gathered by a private university in Ecuador over more than 20 years, to normalize them and to parameterize a multi-layer perceptron (MLP) neural network, whose best-performing configuration would be used as a benchmark for the comparison of more recent and sophisticated AI techniques. However, the scan of hyperparameters for the MLP —exploring more than 12,000 configurations— revealed no correlations between the input variables and the chosen metrics, suggesting that there is no gain from applying advanced AI on the extensive socio-economic data. This finding contradicts the expectations raised by previous works in the related literature, in some cases highlighting important methodological flaws.