This is a project to develop a predictive model for demand driven purchases of ebooks for an academic library. The model inputs are purposefully kept limited and do not use any patron identifying information.
The model was build using SAS Enterprise Miner (including Text Miner). A combination of Base SAS and Python programs were used to build the training data set.
The repository includes:
- An XML file that can be imported into SAS Enterprise Miner to create a diagram workspace.
- Python scripts used to retrieve data summary data and various MARC fields.