I’ve combined the example script with the era boosting script to create a low memory, “high performance” solution. I’ve tested it several times and total memory usage is around 13GB (edit: 16GB on data load, see post below). On an 8 core machine (no threads), it takes a little over an hour for the initial run.
Data is “int8”
The feature set is “medium”
Training Era = every 4th.
The era boosting portion saves each iteration as a model for additional testing and analysis. Parameters here are random, you’ll want to do additional testing
Results from one of the iterative models.