CIS - Final Data Mining Chp 1&2
What is organizational data?
Data collected by an organization to address a specific question.
What is deployment?
Sixth step of CRISP DM. Takes results of mining and puts them into practice.
What is the purpose of CRISP DM?
The process for data mining separated into six steps.
What is Data Mining?
The process of analyzing data sets, that are large in nature, in statistical and logical methods, to find patterns.
What is normalization?
The process of breaking data into multiple tables to reduce redundancy.
What is data analysis?
The process of examining data in a structured way to extract a meaning.
What is denormalization?
The process of removing organization from data, for faster querying.
OLAP =
online analytical processing
OLTP =
online transaction processing
What are the six steps in order?
Business understanding, data understanding, data preparation, modeling, evaluation and deployment.
What are data warehouses?
A lard scale repository for archived data, which are available for analysis.
What are observations?
A row of data in a data set
What are databases?
A structured organization of facts so they are easily accessible.
What is data?
Any arrangement or compilation of facts. Can be structured or unstructured.
What is a data set?
Any compilation of data that is suited for analysis.
What is modeling?
Fourth step of CRISP DM. Developing a computerized representation of observations.
CRISP-DM =
Cross Industry Standard Process for Data Mining
What is operational data?
Data that is generated by day to day work.
What is OLTP?
Database concept where data is collected and organized that allows for fast and repeated transactions.
What is OLAP?
Database concept where data is organized to allow for analysis not practical work.
What are tables?
Database containers.
What is archived data?
Datat that has been copied out a live database and into a warehouse, where it can be analyzed.
What is evaluation?
Fifth step of CRISP DM. Reviewing the results and interpreting the results.
What is business understanding?
First step of CRISP DM. Helps understand the organization's goals in relation to tasks. Must ask why process is going on.
What are attributes?
One column.
What is data understanding?
Second step of CRISP DM. Seeking out the sources of the data. Develops comprehension of where data comes from, how it is collected and its meaning.
What is data preparation?
Third step of CRISP DM. Ensuring data to be mined is cleaned and ready. Handles inconsistent data or other problems.
