• Contents:

Amazon Personalize

Ref: https://www.udemy.com/course/aws-ai-practitioner-certified/learn/lecture/44887675

• 🔧 Real-time personalized recommendations
  • e.g. personalized product recommendations, re-ranking, customized direct marketing…
  • Fully-managed ML service
• Uses same technology used by Amazon.com
• Integrates well into existing websites and applications
• Use cases: retail stores, media, entertainment…

Amazon Personalize Recipes

• Recipes = algorithms prepared for specific use cases
• Customers must provide the training configuration on top of the recipe
• Example recipes:
  • Recommending items for users (USER_PERSONALIZATION recipes)
    • User-Personalization-v2
  • Ranking items for a user (PERSONALIZED_RANKING recipes)
    • Personalized-Ranking-v2
  • Recommending trending or popular items (POPULAR_ITEMS recipes)
    • Trending-Now, Popularity-Count
  • Recommending similar items (RELATED_ITEMS recipes)
    • Similar-Items
  • Recommending the next best action (PERSONALIZED_ACTIONS recipes)
    • Next-Best-Action
  • Getting user segments (USER_SEGMENTATION recipes)
    • Item-Affinity

Amazon Mechanical Turk (MTurk)

Ref: https://www.udemy.com/course/aws-ai-practitioner-certified/learn/lecture/44887679

• 💡 Origin: Chess Mechanical Turk → https://en.wikipedia.org/wiki/Mechanical_Turk
  • Image
• 🔧 Crowdsourcing marketplace to perform simple human tasks
  • Distributed virtual workforce
• Example:
  • You have a dataset of 10 million unlabeled images
  • You distribute the task on Mechanical Turk and humans will tag/label those images
  • You set the reward per image (e.g. $0.10 per image)