Perfomalist - Change & Anomaly Detection

PERFOMALIST - Weekly Data Profiler and Perfomalies (performance anomaly) Detector. Functionality - Weekly data profiling to visualize patterns, anomalies and short term seasonality via IT-Control Charts. Method - SPC/MASF based Statistical Exception and Trend Detection (SETDS) Output - IT-Control Chart (see example below) Data cube with summarized data (168 rows/weekhours) Requirement - Input data should consist of at least 3 weeks of history as the method requires comparing the last 7 days of data (actual) with at least 2 weeks long learning/reference data set (baseline).