Robot-to-Robot¶

This section pulls back the curtain to reveal what DataRobot employees talk about in Slack. No surprises here—data science is still top of mind.

Use case	Description
Single- vs. multi-tenant SaaS	What's the difference between the two deployment options with respect to DataRobot SaaS?
ACE score and row order	How is sampling done in EDA2 when calculating ACE scores?
Redundant features explained	What makes a feature redundant?
Import .tf or .keras?	Have you looked at custom models?
N-grams and prediction confidence	What tools help understand n-gram predictions?
GPU vs. CPU	What's the difference between GPUs and CPUs?
Prediction Explanations on small data	Can you get Prediction Explanations for a small dataset?
Neural nets and tabular data	Do you need neural networks for tabular data?
PCA and K-Means clustering	What's the impact of PCA on KMeans?
Default language change with Japanese	Why did the default language change when modeling Japanese text features?
Let's talk target leakage	Why might target leakage show intermittently?
Normalizing for monotonicity	Can you help me with monotonicity?
An interesting way to use a payoff matrix	Consider justifying cost vs. identifying profit drivers.
Target transforms	How does transforming your target help ML models?
Dynamic time warping	What should I look out for with dynamic time warping?
Multiple reduced feature lists	Can I have multiple Reduced Features lists for one project?
NPS in DataRobot	Has anyone worked with net promoter scores (NPS)?

Was this page helpful?