Strategic Economic Decision-Making: Using Bayesian Belief Networks to Make Complex Decisions.

摘要

By nature, big data stored or warehoused in organizational storage facilities does not immediately suggest courses of action to maximize revenues, minimize costs or does it suggest optimal results. The challenge of any organization is to extract actionable business intelligence solutions from these data. We suggests the use of the BayeSniffer algorithm as a unique discrete data-sniffing tool to translate structured data into business intelligence through a Structured Query Language (SQL) server-based approach. The concept of the BayeSniffer follows empirical research on Bayesian belief networks (BBN) and the publication of Strategic Economic Decision- Making: Using Bayesian Belief Networks to Solve Complex Problems (Grover, 2013). We interpret the results of the BayeSniffer inductively to provide a consistent translation of the analysis we obtain from the use of BBN. With the deluge of data- mining protocols available in the market today, our niche is evaluating structured data information and translating it into business intelligence using conditional probabilities derived from the axioms of set theory and Bayes' theorem. This white paper gives an overview of the problems organizations face, suggests the use of the BayeSniffer algorithm as a solution, reviews Bayes' theorem as it applies to the algorithm, and gives a real-world example of our data sniffing statistical capabilities.