Predicting Job Performance with a Fuzzy Rule-Based System

Classification problems affect all organizations. Important decisions affecting an organization's effectiveness include predicting the success of job applicants and the matching and assignment of individuals from a pool of applicants to available positions. In these situations, linear mathematical models are employed to optimize the allocation of an organization's human resources.

Use of linear techniques may be problematic, however, when relationships between predictor and criterion are nonlinear. As an alternative, we developed a fuzzy associative memory (FAM: a rule-based system based on fuzzy sets and logic) and used it to derive predictive (classification) equations composed of measures of job experience and job performance. The data consisted of two job experience factors used to predict measures of job performance for four US Air Force job families. The results indicated a nonlinear relationship between experience and performance for three of the four data sets. The overall classification accuracy was similar for the two systems, although the FAM provided better classification for two of the jobs. We discuss the apparent nonlinear relationships between experience and performance, and the advantages and implications of using these systems to develop and describe behavioral models.