Free Trial

Safari Books Online is a digital library providing on-demand subscription access to thousands of learning resources.

  • Create BookmarkCreate Bookmark
  • Create Note or TagCreate Note or Tag
  • PrintPrint
Share this Page URL
Help

8. Building Price Models > k-Nearest Neighbors

k-Nearest Neighbors

The easiest approach to our wine pricing problem is the same one you would use if you were trying to price something manually—that is, to find a few of the most similar items and assume the prices will be roughly the same. By finding a set of items similar to the item that interests you, the algorithm can average their prices and make a guess at what the price should be for this item. This approach is called k-nearest neighbors (kNN).

Number of Neighbors

The k in kNN refers to the number of items that will be averaged to get the final result. If the data were perfect, you could use k=1, meaning you would just pick the nearest neighbor and use its price as the answer. But in real-world situations, there are always aberrations. In the example, you deliberately add “noise” to simulate this (the random addition or subtraction of 20 percent). Someone might get a great deal, or an uninformed customer might drastically overpay for the nearest neighbor. For this reason, it’s better to take a few neighbors and average them to reduce any noise.


  

You are currently reading a PREVIEW of this book.

                                                                                                                    

Get instant access to over $1 million worth of books and videos.

  

Start a Free Trial


  
  • Safari Books Online
  • Create BookmarkCreate Bookmark
  • Create Note or TagCreate Note or Tag
  • PrintPrint