A feed-forward artificial neural network (ANN) has been developed for predicting the aquatic ecotoxicity of alcohol ethoxylate (AE), a non-ionic surfactant comprising a variety of homologues. Trained with previously reported ecotoxicity data, the ANN utilizes both molecular characteristics (alkyl chain length, branching extent in alkyl chain, and ethoxylate (EO) number) and exposure features (effect endpoint, test duration, test type, and species taxon) as inputs to predict the ecotoxicity. The ANN predicted an increase in ecotoxicity for homologues with a longer or less-branched alkyl chain, or those with fewer EO units. But for long alkyl chain (>14) homologues, the ecotoxicity increase was predicted by the ANN to level off, which is obscured by existing quantitative structure-activity relationships (QSARs). A "leave-one-out" cross-validation process indicated that the prediction accuracy was within a factor of 5 with 90% probability. This research demonstrated that the current ANN covers a wider application domain with respect to the homologue range and a variety of exposure features without compromising on predictive accuracy.