Here's an excerpt:
You can read the rest over at the blog.The item-based design approach has the goal of allowing data input in a flat, tabular format without giving up the browsability and analytic capability of highly dimensional cubes. It also separates input from reporting in a very elegant fashion.
You begin with an input cube, which should have only the basic dimensions, plus a measures dimension to represent the columns of the input table, and item dimension to represent an arbitrary number of rows.
The measures dimension will include many string elements which map to other dimension elements. Thanks to the picklist feature in TM1 9.5+, these lists can even be restricted to ensure invalid entry does not occur.
A separate reporting cube is then created that maps the string elements to actual dimensions, for reporting and analysis, usually via rules. This cube has no data entry and populates itself entirely from data in the input cube. You could also use TI to populate such a cube without too much trouble, for implementations that have higher data volumes.
Let me know if you'd like me to keep posting here about future blog articles.