Big data is usually defined as lots of records and fields with large variety, volume, and velocity. But big data by itself is of no value; it’s the information in the big data that determines its value. If the records contain little information, it’s obvious that more records containing little information will be of little help in predictive modeling. Consider a behavioral data collected on a retailer’s web site. Time on site, even for millions of visits will provide some information, but little truly valuable information to help us predict whether or not someone will purchase soon. Additional information, such
To view this content
OR subscribe for free
Already receive the Predictive Analytics Times emails?
Click here to complete this one-time subscription upgrade
As of January 2014, the Predictive Analytics Times now requires legacy email subscribers to upgrade their subscription - one time only - in order to attain a password-protected login and gain complete access.