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)? |
Updated March 3, 2023
Was this page helpful?
Great! Let us know what you found helpful.
What can we do to improve the content?
Thanks for your feedback!