Applying Azure Machine Learning service to drive success of API programs
summary
Built an Azure Machine Learning pipeline that ingests API analytics and produces a developer scoring model to classify accounts into segmentation into stages (exploring, evaluating, onboarding, production), using labeled historical usage as training data and the API management logs as features. Early experiment produces meaningful clusters that surface inactive versus production users and drives targeted outreach, but accuracy depends on volume and requires continuous retraining as new APIs and partners change patterns; integration works with any API management platform and the team invites more data to improve the model.
AI-written summary · about
chapters (7)
- 0:00Start
- 1:37Traditional sales pipeline
- 2:29Adoption Pipeline
- 8:06Segmenting API developers
- 10:09Weight game
- 11:30Using Azure ML to segment developers
- 12:27What is next?
related talks
41mLeveraging Automated Machine Learning to enable anyone to develop Machine Learning solutions
23mMachine Learning powered API governance
01h 05mAzure Machine Learning for the Developer
58mDeep Dive into Azure Automated Machine Learning
49mEnhanced AML fraud detection solutions with Azure Machine Learning
43mA lap around Azure Machine Learning services
51mTaking Models to the Next Level with Azure Machine Learning
01h 01mAI and ML imbedded in Azure Data Platform