All Questions
1 question
- Bountied 0
- Unanswered
- Frequent
- Score
- Trending
- Week
- Month
- Unanswered (my tags)
0votes
1answer
664views
How to compare test vs train model performance
When comparing the test vs train model performance to ensure no overfitting (e.g., using AUC ROC as an example), is it better to select the model with the largest test score, or the model with the ...
- The Overflow Blog
- Featured on Meta
Hot Network Questions
- Why did Germany allow and help introduce the Deutsche Mark to Montenegro?
- Creating "flag" background for labels using QGIS
- Which Western countries are looking to cancel procurement/collaboration programs for US weapon systems and how far has that proceeded?
- How to convincingly erase a population's memory?
- Find indeterminate limit without using L'hopital's theorems
- In Widows, what is Amanda referring to when she says, "I got the impression from Jimmy he wasn't so sure about this one"?
- How could technological development be significantly accelerated without a major war?
- Implement PHMINPOSUW (Packed Horizontal Word Minimum)
- Shakespeare's use of the word "excursion"
- Could OLS miss statistically significant coefficient because it's too small?
- I'm owed money from a non-profit for services rendered, but they are unresponsive
- Suggestion for data analysis with meteorological data
- Boids by Simon Woods: can we re-invent further efficient flocking models to forge complexity from simple rules?
- Riddle in Cheshire Crossing comic
- Can the irrationals be partitioned into dense, disjoint subsets?
- Doubt regarding center of mass of a cone
- What is this orange button on my antique Black & Decker drill?
- Double underline single label for bird ecology (BTO) notation in QGIS
- Can we have direct or indirect speech after the verb "lie"?
- There are no employees at the store. Why not?
- Alternatives for writing a formula
- Retrieval-Augmented Generation from text files
- What is tunneling? What does it mean to carry a service not normally provided by the network?
- Revising part of a manuscript not covered by the referee report