| The important processes that have to be | | | | |
| clearly delineated for Data Mining, Analysis | | | | Much of the data that they have will have |
| and Modelling are: | | | | different frequencies of change, refreshment |
| | | | or occurrence. It will be kept for different |
| Data model: what data will be available and | | | | periods. In some cases, aggregated data may |
| how will it flow? | | | | be kept rather than source data. All of these |
| | | | factors effect the data modelling exercise |
| Data gathering: how will data be gathered | | | | and the eventual modelling software |
| both in physical and technological terms? | | | | requirements. |
| | | | |
| Data gathered: what data will be gathered? | | | | Turning the data into useful information |
| | | | requires: |
| Data types: what types of data will be | | | | |
| gathered? | | | | Identifying the issue(s) |
| | | | |
| Data formatting: how will data be held? | | | | Assembling the data set(s) |
| | | | |
| Data warehousing: where will data be held? | | | | Building models |
| | | | |
| Data mining: how will we retrieve data from | | | | Verify models |
| the warehouse? | | | | |
| | | | Interpretation of the results |
| Information modelling: how will we create | | | | |
| models and what of? | | | | Automation of the delivery |
| | | | |
| Information access: how will we access the | | | | Thereafter, modelling tools and techniques |
| data models and reports? | | | | have to be used. These can be divided into |
| | | | two groups: theory driven and data driven. |
| Presentation & reporting: on what will we | | | | |
| report? | | | | Theory driven modelling (hypothesis testing) |
| | | | attempts to substantiate or disprove |
| Most companies want to know essential | | | | preconceived ideas. Theory driven modelling |
| information about customers at every point of | | | | tools require the user to specify most of the |
| contact, for example: | | | | model based on prior knowledge and then tests |
| | | | to see if the model is valid. |
| Lifetime value | | | | |
| | | | Data driven modelling tools automatically |
| X sell and upgrade potential | | | | create the model based on patterns they find |
| | | | in the data. This also needs to be tested |
| Acquisition cost | | | | before it can be accepted as valid. |
| | | | |
| Channel preferences | | | | Modelling is an iterative process with the |
| | | | final model usually being a combination of |
| Loyalty/retention | | | | prior knowledge and newly discovered |
| | | | information. |
| Purchase behaviour patterns | | | | |