SIT717 Enterprise Business Intelligence

Your view on Data mining Tools or Systems and how it can be applied in business intelligence. Can we always trust what discovered by a data mining system?Interesting/potential new applications of data mining to Business intelligence.Discussion about specific techniques and technical details.

 A number of data mining approaches have been available for use. However, the issue of reliability becomes very critical. One important question is, “is discovered knowledge fully reliable?” Another important aspect is if it effectively reflects the regularities hidden in transaction data. 

Data quality is the first factor affecting reliability Two aspects of data quality are noise and incompleteness, and class imbalance Noise and incompleteness  is a common factor affecting reliability Discovered knowledge could also encounter class imbalance, which could affect reliability 

 

Knowledge granularity is an important factor affecting reliability This is especially important in retain knowledge discovery Example, the associations considered in market basket analysis Sometimes certain associations could be impractical; therefore, affecting data reliability. 

 

Different information could change over time Patterns and data hidden in various databases may also change over time. To ensure data reliability, knowledge discovery needs done in a dynamic manner. Knowledge discovery may be unreliable using static way without capturing the dynamics 

 

Measured through repeating  test over same population Some studies indicate that this technique could not be relied upon since repeated tests could change Consistency may be assessed using test scores from different occasions If results from different tests are consistent, then discovered knowledge is reliable 

Dai, H., Liu, J. N. K., & Smirnov, E. (2012). Reliable knowledge discovery. New York: Springer.  Holsheimer, M., & Siebes, A. P. J. M. (1994).

 

Data mining: The search for knowledge in databases. Amsterdam, the Netherlands: Centrum voor Wiskunde en Informatica.