I am looking for a definition of Data Scout.
what is the difference between Data Mining and Data Scout?
Data Science Stack Exchange is a question and answer site for Data science professionals, Machine Learning specialists, and those interested in learning more about the field. It only takes a minute to sign up.Sign up to join this community
In business, there is little time to look through the data that has been eliminated before a specific analysis project so I put that data in an elim_bin (project code#, project date) I ALWAYS attach data source & date pulled for each eliminated.
Later, I can "scout" that data with an algorithm to see if something could be useful/learned.
This is how I use "scout" data. Hope this helps.
Copying from the abstract I found here - read the paper for more insights:
In the year 2011, the CMS collaboration introduced the novel concept of data scouting, allowing to take data that otherwise would be rejected by the usual trigger filters. This special data flow, based on event-size reduction, was created to maintain sensitivity to new light resonances decaying to jets or muons, with very small online and offline resources allocated to it. The challenges implied by this new workflow and the solutions developed within the CMS experiment are shown. This technique is now a standard ingredient for CMS data-taking strategy. The present status of data scouting in CMS is presented.
I do not come from a Physics background, and hence I could not completely understand the context while reading the paper in the larger scheme of things. But atleast this gives you a heads up about what it is.
Coming to Data Mining, there are plenty of definitions you can find. My definition would be using raw data to find patterns or insights from large datasets. This could be done with the use of many algorithms from math, computer science or statistics.
Some data mining algorithms are k-nearestneighbor, k-means, naive bayes, and so on.
So what is the difference between data scouting and mining? In mining, you consider raw datasets and perform some operations. In scouting, if I am not wrong, you take the data discarded by some filters (do not know what these filters are) while performing some operation, and then considering that data to perform additional operations.