Improving predictive accuracy with a combination of human intuition and mechanical decision aids

This study examines the intuitive combination of human judgment and mechani cal prediction under varied information conditions, As expected, mechanical prediction outperformed human intuition when based on the same information , but a combined approach was best when judges had access to relevant infor mation not captured by the model (information asymmetry), The model was use ful for differentiating between the event outcomes (improved slope), while eliminating the bias caused by base-rate neglect. Human intuition was usefu l for incorporating relevant information outside the scope of the model, re sulting in improved slope and reduced judgment scatter. The addition of irr elevant information was detrimental to judgment accuracy, causing an increa se in bias and a reduction in slope. These results provide insight into hou r and when combining mechanical prediction and human intuition is likely to result in improved accuracy. (C) 1998 Academic Press.