Satisficing Metric
A satisficing metric is an evaluation measure that only needs to meet a preset threshold rather than be optimized as far as possible. For example, if a customer-support tool must respond within 80 milliseconds, response time is a satisficing metric with an upper limit of 80 ms.
0
1
Tags
Machine Learning
Deep Learning
Supervised Learning
Dive into Deep Learning @ D2L
Data Science
Machine Learning Strategy
Machine Learning Yearning @ DeepLearning.AI
Related
Primary Optimization Metric
Using Hard Limits and One Score to Compare Models
Shared Evaluation Metric Lets a Team Move Faster
Latency limit versus F1 score
What Counts as a Satisficing Metric
Combining Multiple Evaluation Criteria
Choosing the Right Evaluation Metric
Applying Satisficing and Optimizing Metrics
Explaining Optimizing and Satisficing Metrics
Choosing a deployment metric under a hard device limit
Why Latency Is a Satisficing Metric
What does a satisficing metric ask for?
When a system has both an optimizing metric and a satisficing metric, the best plan is to maximize the optimizing metric even if the satisficing metric is violated.
Voice-Trigger Detection: Minimizing Misses Under a False-Alarm Constraint
Satisficing Metric
Learn After
What is the key idea behind a satisficing metric?
A satisficing metric must be maximized as much as possible before a model can be considered acceptable.
A satisficing metric only needs to be _____ once it reaches an acceptable threshold.
Match each satisficing-metric term to its meaning in a delivery-delay example.
Order the Steps for Making Latency a Satisficing Metric
Why a latency threshold can simplify model selection
Choose the model that satisfies the time limit and gives the better score.
Using a 100 ms runtime cutoff as a satisficing metric
What response-time limit is used in the example as an acceptable threshold?
A satisficing metric is acceptable once it clears a preset threshold.