Autoencoders for strategic decision support

In the majority of executive domains, a notion normality is involved in most strategic decisions. However, few data-driven tools that support decision-making are available. We introduce and extend use autoencoders to provide strategically relevant granular feedback. A first experiment indicates experts inconsistent their decision making, highlighting need for support. Furthermore, using two large industry-provided human resources datasets, proposed solution evaluated terms ranking accuracy, synergy with experts, dimension-level This three-point scheme validated (a) synthetic data, (b) perspective data quality, (c) blind expert validation, (d) transparent evaluation. Our study confirms several principal weaknesses stresses importance between model humans. Moreover, unsupervised learning particular autoencoder shown be valuable decision-making.