(March 25, 2005) -

Amazon.com Statistically Improbable Phrases

Amazon.com's Statistically Improbable Phrases, or "SIPs", show you the interesting, distinctive, or unlikely phrases that occur in the text of books in Search Inside the Book. Our computers scan the text of all books in the Search Inside program. If they find a phrase that occurs a large number of times in a particular book relative to how many times it occurs across all Search Inside books, that phrase is a SIP in that book
.- Amazon Website

It all must sound terribly abstract at this point. Here are some Amazon examples:

load forecaster, imaginary blossoms, sick morning, life purpose statement, sip test, social epidemics, profit per customer visit, biggest strength

In each case, the link will take you to a list of books that share the SIP. Is there commonality amongst the results? You can see for yourself that, in some cases the answer is very clear while in others the jury might be out. From here, it looks like the more literary the idea the less likely there is commonality. The more that the idea is religious, technical or business-y the more likely that the results show a conceptual relationship.

(Odd...we've never considered the idea that technical, religious and business terminology might have something in common.)

So, a Resume SIP (RSIP) would be a term that occurs a large number of times in a single resume relative to the number of times it occurs in all resumes. A Job SIP would be the same thing for a job. We believe that matching, focused on unique attributes (rather than common attributes) is more likely to produce interesting and useful results. It's realistic to imagine that there is an observable fingerprint in a Resume.

There is certainly an inverse proposition: the Missing Standard Phrase. If an SIP represents a positive difference from the norm, than an MSP would be its negative. This resume is like all of the others in the set except it's missing the following phrases.

As we said yesterday search is a technical fix to a problem that can be addressed in other ways. If you are going to pursue recruiting with a mindset that requires search, then the SIP is going to make a serious difference in your productivity. It is a method that eliminates any question of bias based on meaning.

John Sumser

Take a quick look at Industry News, read the Bugler.

---

| Home | ERN | Bugler | The Blogs | Blogroll | Advertise | Archives |

---

Contacting Us: