Glossary term
Glossary term
Evaluation and Benchmarks
A function that identifies the frequency of data samples having exactly a particular value. When a dataset's values are continuous floating-point numbers, exact matches rarely occur. However, integrating a probability density function from value x to value y yields the expected frequency of data samples between x and y.
For example, consider a normal distribution having a mean of 200 and a standard deviation of 30. To determine the expected frequency of data samples falling within the range 211.4 to 218.7, you can integrate the probability density function for a normal distribution from 211.4 to 218.7.
For example, consider a normal distribution having a mean of 200 and a standard deviation of 30. To determine the expected frequency of data samples falling within the range 211.4 to 218.7, you can integrate the probability density function for a normal distribution from 211.4 to 218.7.
Created for this library
A risk team uses the probability density function of historical losses to size value-at-risk thresholds for portfolio reporting.
A research team uses kernel density estimation of the probability density function of latency to detect tail-shape changes between releases.
An operations team uses the probability density function of delivery times to choose a service-level promise that covers a target fraction of orders.
Definition source: Google for Developers Machine Learning Glossary | Creative Commons Attribution 4.0 License