Big Data Computing Applications - Guide to Cloud Computing for Business and Technology Managers - page 446

TABLE 21.3
Industry Use Cases for Big Dat a

Manufacturing Retail

Product research Customer relationship management

Engineering analysis Store location and layout

Predictive maintenance Fraud detection and prevention

Process and quality metrics Supply-chain optimization

Distribution optimization Dynamic pricing

Media and telecommunications Financial services

Network optimization Algorithmic trading

Customer scoring Risk analysis

Churn prevention Fraud detection

Fraud prevention Portfolio analysis

Energy Advertising and public relations

Smart grid Demand signaling

Exploration Targeted advertising

Operational modeling Sentiment analysis

Power-line sensors Customer acquisition

Health care and life sciences Government

Pharmacogenomics Market governance

Bioinformatics Weapon systems and counter terrorism

Pharmaceutical research Econometrics

Clinical outcomes research Health informatics

tools allow the processing to be expressed in terms of dataflows and
transformations incorporating new dataflow programming languages
and shared libraries of common data manipulation algorithms such
as sorting. Conventional supercomputing and distributed computing
systems typically utilize machine-dependent programming models
that can require low-level programmer control of processing and node
communications using conventional imperative programming lan-
guages and specialized software packages, which adds complexity to
the parallel programming task and reduces programmer productivity.
A machine-dependent programming model also requires significant
tuning and is more susceptible to single points of failure.

3. Focus on reliability and availability : Large-scale systems with hun-
dreds or thousands of processing nodes are inherently more sus-
ceptible to hardware failures, communications errors, and software
bugs. Big data computing systems are designed to be fault resilient.
This includes redundant copies of all data files on disk, storage
of intermediate processing results on disk, automatic detection of
node or processing failures, and selective recomputation of results.