Larry Proctor

A smarter process for sensing the information space

As a result of the growth of the Internet, the amount of available information is exponentially increasing. However, increasing the amount of information does not imply increasing usefulness. Furthermore, as the complexity of business relationships increases, there is a natural tendency toward less structured interaction between entities. This highlights the growing relevance of unstructured information in documenting the interactions of organizations and individuals. Analyzing and making sense of this unstructured information space requires more than text-mining algorithms; it requires a strategic approach. We propose a unified approach that addresses a variety of information space analytics problems. Our method for making sense of unstructured data is described by six steps that are analogous to the algebraic order of operations PEMDAS (parenthesis, exponent, multiplication, division, addition, and subtraction). These basic text-mining operations can be combined in many interesting ways to handle a diverse set of problems, and just as in algebra, it is critical that these operations be performed in the correct order to guarantee a meaningful result. In this paper, we describe how PEMDAS has been implemented within organizations to enable decisions that produced measurable business value.

Analytical Pathway Methodology: Simplifying Business Intelligence Consulting

The implementation and use of advanced analytics to identify patterns and discover the non-obvious from structured and unstructured data sources to improve business performance or establish a competitive advantage is becoming more commonplace in enterprises. Delivering complex advanced analytical systems to mine unstructured data sources requires a complex decision-making process by the business analytics user to perform an analysis. In general, analytics is a process that often times requires continual iteration of the content sources(s) to locate, examine and interpret information to address an issue or hypothesis. This problem led us to explore a method to communicate, and eventually automate, an analytical pathway to be implemented with an analytical services system. In this paper we describe some of the challenges in the use of complex advanced analytics for business intelligence, an initial breakdown of the process and an approach to bringing repeatability to the analysis process.

Multi-taxonomy: Determining Perceived Brand Characteristics from Web Data

A strong brand is a major asset to any corporation. Traditional brand image and reputation tracking is limited to news wires and contact centers analysis. However, with the emergence of Web, consumer generated media (CGM), such as blogs, news forums, message boards, and web pages/sites, is rapidly transforming the way companies analyze their brand perceptions. This paper describes the next generation COBRA (Corporate Brand and Reputation Analysis) approach to mining a wide range of CGM content to discover how the social media-based community perceives the brand. The solution processes a diverse set of structured and unstructured information and mines CGM content by generating multiple taxonomies from the data. These taxonomies are then used singly and in combination to better understand important brand characteristics and hence enhance marketing and strategic decision making. We illustrate our approach with a real-world case study involving the Kraft Foodspsila Vegemite brand.