⚓ T370523 [EPIC] Run UI-less experiment comparing API recommendation quality
Page MenuHomePhabricator

[EPIC] Run UI-less experiment comparing API recommendation quality
Open, HighPublicSpike

Description

Background

  • We would like to run an experiment that compares various APIs recommending content independent of the UI. This task will investigate different way to run this experiment and provide a suggestion for the experiment design

User story

  • As a product team, we would like to compare some of our recommendation based APIs so we can choose the one that will help readers learn the most

Requirements

  • Investigate different ways to run the experiment and provide a proposal for the experiment design

This task was created by Version 1.2.0 of the Web team task template using phabulous

Event Timeline

ovasileva created this task.
ovasileva renamed this task from [Spike?] Design UI-less experiment comparing API recommendation quality to [Spike] Design UI-less experiment comparing API recommendation quality.Jul 23 2024, 8:36 AM
Jdlrobson removed the point value for this task.Jul 26 2024, 1:54 AM
ovasileva renamed this task from [Spike] Design UI-less experiment comparing API recommendation quality to [EPIC] Run UI-less experiment comparing API recommendation quality.Jul 29 2024, 10:16 AM
ovasileva edited projects, added Epic; removed Spike.

https://github.com/geohci/list-building-interface/issues/18 has some suggestions for improving the suggestions (don't know if this is only about comparing different ones or partly also about improving things or building something new to test here). One could also compare different variants of that "list-building" tool (I also suggested renaming it to e.g. "Related articles finder").