The temporal analysis of crime data produces analytics that describe patterns in criminal activity based on time. You can analyze temporal crime data to develop prescriptive analytics, either through traditional crime analysis means or through a data science approach. Knowing how to produce prescriptive analytics from temporal crime data allows you to provide decision-support to law enforcement agencies that want to optimize their tactical crime fighting.
For purposes of this discussion, consider temporal data to be tabular data that's earmarked with date/time entries for each record in the set. You use temporal data analysis to make inferences and draw correlations that you can use to monitor and predict what crimes are happening when and why. In crime analysis, an example of a temporal dataset would be a dataset that describes the counts of different types of crimes that have been committed, broken into count per day and recorded on a daily basis for an entire month.
To be successful at deriving simple, yet useful, insights from temporal crime data, you need only a basic skill level in data science. You should know how to draw fundamental statistical and mathematical inferences, how to spot and investigate outliers, how to analyze patterns in time series, and how to draw correlations or causations through regression techniques. When deriving insights from temporal crime data, you generally produce decision-support products in the form of tabular data reports and simple data visualizations — such as bar charts, line charts, and heat map charts.