ABSTRACT
Data mining is the sifting through of voluminous data to extract knowledge for decision making. This article illustrates the context, concepts, processes, techniques, and tools of data mining, using statistical and neural network analyses on a dataset concerning employee turnover. The resulting models and their predictive capability, advantages and disadvantages, and implications for decision support are highlighted.
Subject(s)
Child Welfare/statistics & numerical data , Decision Support Systems, Management , Government Programs , Personnel Turnover/statistics & numerical data , Social Work , Child , Humans , Neural Networks, Computer , Policy Making , Systems Integration , United States , WorkforceABSTRACT
Nationwide, social services agencies continue to report difficulties in the retention of public child welfare caseworkers. As service demands placed on the child welfare system continue to increase, the need for an experienced and competent work force becomes imperative. Previous studies have identified the reasons for the high turnover rate among child welfare caseworkers. This article reports the findings of an exploratory study to identify factors that may influence some caseworkers to continue employment in public child welfare when so many others are leaving. From comprehensive focused interviews with 23 caseworkers, the following four factors of retention emerged: (1) mission, (2) goodness of fit, (3) supervision, and (4) investment. The importance of the relationship with the agency and the four factors in the retention of public child welfare caseworkers is discussed.