Tag Archives: BigData
Documents and Data Mining
Vector representation of documents provides a natural framework for classifying documents so either supervised classification for documents that have labels assigned or unsupervised learning – clustering – for unlabeled documents can be employed in the analysis. Since typical term-vectors are … Continue reading
What should we expect of the Data Scientist?
What should we expect of the Data Scientist? That they should have good working understanding of the business and of the specific business process that the analysis will support. That they should understand the thinking style and the types of … Continue reading
What is the best action or outcome?
Prescriptive Analytics answers the question, “What is the best action or outcome?” The key is to provide new ways to improve certain types of performance that is documented in the business and analytics problem statements. This methodology provides specific quantifiable … Continue reading
Data Transformation – Unsupervised Discretization
Discretizing Numeric Attributes Why? Some classification and clustering algorithms operate with nominal only and can not operate with attributes measured on a numeric scale. Statistical clustering methods often assume numeric attributes have a normal distribution. Some algorithms repeatedly sort the … Continue reading
Naive Bayes approach to Data Mining
Simple yet powerful. The approach uses all the attributes. Assumes that the attributes are equally important – that they are statistically independent – (Naive) – knowing the value of one says nothing about the value of the other. Probability of … Continue reading
How integrated is Analytics with enterprise strategy?
The organization should understand the full potential of Analytics and whether it should put more effort into optimizing and maturing the deployment. Is there a link between enterprise strategy and Analytics? Is it used only on an ad hoc basis? … Continue reading
Framing the problem – Analytics
A frame consists of an outline or model of interpretation that people rely on to understand and respond to events. People do not look at an event and apply a frame to the event, they use interpretive frames to understand … Continue reading
Enterprise Analytics Center of Excellence
It includes Analytical competencies, Business competencies and IT competencies. The enterprise ACOE is an organization entity which promotes a strong voice to address knowledge management. It maximizes the impact of Analytics initiatives and available resources. It aligns the business needs … Continue reading
Is it an Analytics Solution?
Is the answer and the change process part of the organizations’s control? Does the data exist or can it be obtained? Can the problem be solved and modeled? Can the organization accept the answer (solution)?
Selecting your Analytics Methodology – Considerations
The methodologies are scientific, yet the method of selection is both an art and a science. A problem can be solved with several methodologies. It is important to determine the level of detail of the methodology. The accuracy will vary … Continue reading
Richard A Denman's Blog 