Using Splunk to Predict Health Care
Splunk is seen as a great tool for cybersecurity, but it does a whole lot more, including implementing machine learning. In this case we will take a population dataset from US states, and try and predict the Cancer DR (Death Rates). The data set we will use is [here]:
Now, we will use a Predict Numeric Field experiment:
Next we create a new experiment:
Initally we will use Linear Regression to determine the numeric value of the Cancer DR:
Next we will use all the other fields in the data set — apart from the RegionState and Population Density — to train against: