employing analytical methods to predict treatment impact (i.e., medical influence) similar to the uplift modeling techniques used for marketing treatment decisions.

we need a model that scores according to the likelihood an individual’s behavior will be influenced. We need an uplift model:

As with all sources of data, to leverage its predictive potential, the mood barometer must be combined with other data sources.

“Who is leaving but would stay if we contacted them?” This sounds pretty convoluted.

“The potential benefits of mining such data [from cell phones that track location via GPS] are various; examples include reducing traffic congestion and pollution, limiting the spread of disease, and better using public resources such as parks, buses, and ambulance services.

At our disposal we have a detailed manifestation of how the world works: data’s recording of what happened. From that we seek to generalize, to draw grand conclusions, to ascertain patterns that will hold true in situations not yet seen. We attempt to reverse engineer the world’s laws and principles. It’s the discovery of the method in the madness.

By tapping the public’s mood and opinions, they’re trying to predict it all: Product sales. Top music hits. Movie box-office revenue. Academy Award and Grammy winners. Elections. Unemployment statistics.

Prediction helps. Predictively scoring and ranking transactions dramatically boosts fraud detection. A team of enforcement workers can inspect only a fixed number of suspected transactions each week.

YouTube gains an hour of video each second. Estimates put the World Wide Web at over 8.32 billion web pages.