Serverless ML’less recommendation engines

  • Machine learning and AI
  • Huge computation needs
  • The cost involved in the recommendation
  • Accuracy in predictions and so on
Google Recommendations/Retail AI
AWS — Personalize
Adobe Target — Personalization
  1. Collective product catalog
  2. Unified user events
  3. Tune the algorithm based on the business needs
  4. Algorithm tuning interval
  5. Determine placement of the recommendation in the application
  1. A/B testing
  2. Multivariate testing
  3. User engagement
  4. Business promotions
  5. Alternate items based on the available inventory
  6. Sales predictions
  1. As all processing happens under the cover, debugging gets a bit complicated
  2. Understanding pricing can be a bit tricky
  1. How to avoid unconscious bias in the recommendation?
  2. What are the ways to introduce new products?

--

--

--

Mobile application and connected-devices development consultant. Enthusiastic and excited about digital transformation era.

Love podcasts or audiobooks? Learn on the go with our new app.

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store
Shankar Kumarasamy

Shankar Kumarasamy

Mobile application and connected-devices development consultant. Enthusiastic and excited about digital transformation era.

More from Medium

API as a Product Business Models

SOLACE Broker Integration With WSO2 API Manager

HLS DAI with Google Ads Manager, AWS Media Tailor and MediaConvert (Part 1)

Introducing Cesium Scheduler