There are strong indications that (Big) data mining can yield clues about future customer behavior or events. A well-known anecdote is about a young woman who received a promotional present at home for the baby she was expecting without knowing that she was pregnant; the pregnancy was detected by analyzing search behavior in combination with analysis of social media activity.
A recent article published by a team of Microsoft researchers Ryen W. White, Eric Horvitz, and John Paparrizos, a Columbia Univrsity graduate student presents the results of a study on early detection of cancer based on online activity. The researchers performed analysis of anonymized queries of people having been diagnosed with pancreatic adenocarcinoma and data of search queries related to symptoms of the decease. Their findings indicate that "..Signals in search logs show the possibilities of predicting a forthcoming diagnosis of pancreatic adenocarcinoma from combinations of subtle temporal signals revealed in the queries of searchers”. This is a quite encouraging result for the early detection that is critical for this form of aggressive cancer. possible victims could be advised to visit a physician much earlier increasing the chances foe efficient treatment
