Unveiling the diverse efficacy of artificial neural networks and logistic regression: A comparative analysis in predicting financial distress

Abstract The prediction of financial distress has emerged as a significant concern over prolonged period spanning more than half century. This subject garnered considerable attention owing to the precise outcomes derived from its predictive models. main objective this study is predict using two types Artificial Neural Networks (ANN) compared Logistic Regression (LR), and will be done by relying on data 12 Algerian companies for 2015-2019. reason choosing these networks in particular, attributed fact that Elman Network (ENN) commonly used network, contrast Feed-forward Distributed Time Delay (FFDTDNN). Regarding choice sample, can similarity temporal range covered their statements, coupled with approximate parity terms asset size. concluded ENN model outperformed LR predicting classification accuracy 100%. On other hand, FFDTDNN 83.33%. Therefore, it asserted ANNs cannot regarded superior (LR) all statuses. Instead, accurate affirm specific exhibit greater efficacy distress, while demonstrate relatively diminished effectiveness.