The high cost and lack of technology for designed sensors for any given contaminant makes them unfeasible for the time being. Since a contaminant intrusion type is generally unknown it is difficult to define the water quality parameters needed to be measured and analyzed to indicate its presence. It is plausible to assume that an auxiliary substance injected into the distribution system will affect the behavior of typically measured parameters (e.g. total chlorine, pH). For this reason the surrogate/indicator approach (i.e. identifying contaminants using regularly monitored water quality and hydraulic measurements), is appealing. This study focuses on interpreting data collected from sensors measuring routine parameters for revealing outliers indicating possible contamination event intrusions. The method presented utilizes Genetic Algorithm (GA) to optimize parameters to better identify contamination events. An example application is presented and results show promise.