Conformed Dimension and Data Mining
Posted by Dylan Wan on April 20, 2015
I believe that Conformed Dimensions are playing a key roles in data mining. Here is why:
A conformed dimension can bring the data together from different subject area, and sometime, from different source system.
The relevant data can be thus brought together. Data Mining is a technique to find the pattern from the historical data. It can help finding the relationships among the data and use it in predication.
Using the HR Analytics as an example.
HR is providing the Human Resource Management.
HCM is further extending the definition to provide Human Capital Management.
The true value of HR or HCM system is to find the correlations between the factors that HR department can controls or can contribute and impact the performance of the enterprise.
One of the aspect of essential functionality provided from BI is for enterprise performance management. Typically way is to measure whether a resource or an organization meet its goal and if not, how they can be improved.
A powerful way to combine these together is to look at any of the performance results that are collected in the BI/EPM system.
- Sales figures by sales
- # of orders entered by clerks
- # of tickets solved by agents
Look the results together with the Inputs
- How do we compensate them?
- Do they have enough training
- How effectiveness of our rewards?
- What are the essential experiences and skills
The results can thus make significant impacts to the organizations.
- Design a new compensation plan
- Design a training plan
- Change the job criteria and hiring/selection criteria
Here the conformed dimension is playing a key role to bring data together.
It also explains why we should use Data Mining on top of data warehouse.