In a previous blog I wrote about 6 potential applications of time series data<\/a>. To recap,<\/span> they are the following:<\/p>\n Here I am focusing on outlier and anomaly detection. Important to note that outliers and anomalies can be synonymous, but there are few differences, although I am not going into those nuances.<\/span><\/p>\n<\/p>\n WHAT IS AN OUTLIER?<\/b><\/span><\/p>\n In terms of definition, an outlier is an observation that significantly differs from other observations of the same feature. If a time series is plotted, outliers are usually the unexpected spikes or dips of observations at given points in time. A temporal dataset with outliers have several characteristics:<\/p>\n WHY DETECT OUTLIERS?<\/strong><\/span><\/p>\n Broadly for two reasons:<\/span><\/p>\n (1) In business applications the project managers should know if an outlier represents an error. Or are there specific reasons they should be concerned of (if undesired) or excited about (if desired).<\/span><\/p>\n (2) In research and statistical modeling projects outliers impact model performance. So they are removed during model fitting to enhance prediction accuracy.<\/span><\/p>\n<\/p>\n REAL WORLD APPLICATION DOMAINS (few of many)<\/b><\/span><\/p>\n compared with the theoretical predicted values (Source: Wikipedia)<\/span><\/p>\n<\/p>\n TOOLS AND METHODS (few of many)<\/b><\/span><\/p>\n Go to Source<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"\n
\n
\n
![](\"https:\/\/lh5.googleusercontent.com\/qAMMCWlp-QTtS5piHmgPgQwG3C6MMXfvXoK3C9jRut2_g20KyCcKaGmK0-tenNvaTpoNhIL3x5nDCogHfxJtYX4BRAllKzu7TgiwEgjXMs-pckcXGfRrojslJiNZc5FUcu3QkkionOHmthoWlw\")
\n