What inspired this Wish List Request?
Demonstrating JMP Pro 17 to a data science team at PepsiCo
Please describe the new or improved feature or solution you would like to see.
Implement the same Tuning Design generation strategy across all platforms. Specifically, the one used for XGBoost and SVM where the design table is automatically generated behind the scenes.
What would the value be to you and/or other users if this new feature is provided?
There are currently 3 different ways to define and tune hyper-parameters in JMP Pro.
1. Provide a design table (Bootstrap Forest, Boosted Tree, and XGBoost)
2. A grid generating algorithm (XGBoost, SVM, Design Explorer, Time Series Forecast)
3. Delete the hyper-parameter and leave the box empty (GenReg with Elastic Net Alpha)
1 and 3 are difficult to use or hidden. 2 is consistently highlighted by customers as the way it should be done.
Is this an external customer request?
Is there a competitive software package that has this feature or solution that we should be aware of?
Many of the data science packages we compete against have automatic hyper-parameter tuning schemes. That most closely match 2 above.
Will this impact a renewal, expansion, or adoption at a customer, and does this put an account at risk if we do not address this?
