This indicates which measurement to use if/when the service automatically
selects the final measurement from previously reported intermediate
measurements. Choose this based on two considerations:
A) Do you expect your measurements to monotonically improve?
If so, choose LAST_MEASUREMENT. On the other hand, if you're in a
situation where your system can "over-train" and you expect the
performance to get better for a while but then start declining,
choose BEST_MEASUREMENT.
B) Are your measurements significantly noisy and/or irreproducible?
If so, BEST_MEASUREMENT will tend to be over-optimistic, and it
may be better to choose LAST_MEASUREMENT.
If both or neither of (A) and (B) apply, it doesn't matter which
selection type is chosen.
[[["Easy to understand","easyToUnderstand","thumb-up"],["Solved my problem","solvedMyProblem","thumb-up"],["Other","otherUp","thumb-up"]],[["Missing the information I need","missingTheInformationINeed","thumb-down"],["Too complicated / too many steps","tooComplicatedTooManySteps","thumb-down"],["Out of date","outOfDate","thumb-down"],["Samples / code issue","samplesCodeIssue","thumb-down"],["Other","otherDown","thumb-down"]],["Last updated 2025-08-20 UTC."],[[["\u003cp\u003eThis page provides documentation for the \u003ccode\u003eMeasurementSelectionType\u003c/code\u003e enum within the \u003ccode\u003eGoogle.Cloud.AIPlatform.V1\u003c/code\u003e namespace, detailing how the service selects final measurements.\u003c/p\u003e\n"],["\u003cp\u003eThe \u003ccode\u003eMeasurementSelectionType\u003c/code\u003e enum offers three options: \u003ccode\u003eBestMeasurement\u003c/code\u003e, \u003ccode\u003eLastMeasurement\u003c/code\u003e, and \u003ccode\u003eUnspecified\u003c/code\u003e, with \u003ccode\u003eUnspecified\u003c/code\u003e defaulting to \u003ccode\u003eLastMeasurement\u003c/code\u003e.\u003c/p\u003e\n"],["\u003cp\u003eThe documentation advises choosing \u003ccode\u003eLAST_MEASUREMENT\u003c/code\u003e if measurements are expected to monotonically improve or if measurements are significantly noisy, while \u003ccode\u003eBEST_MEASUREMENT\u003c/code\u003e is recommended when the system may "over-train".\u003c/p\u003e\n"],["\u003cp\u003eThis webpage contains a comprehensive list of the different versions of the \u003ccode\u003eGoogle.Cloud.AIPlatform.V1.StudySpec.Types.MeasurementSelectionType\u003c/code\u003e class, from version 1.0.0 all the way to the latest version 3.22.0.\u003c/p\u003e\n"]]],[],null,[]]
