Building in-house recommendation engines – Celine Xu, Axel Johnson

Provide the insights about the important elements need to be considered for building an in-house recommendation system. How could maximize the usage of in-house reco engine. General introduction/summary about major methods/implementations of building recommendation system as well as the limitations/challenges of in-use algorithms.

Key Takeaways

  • Recommendation system is basically a scoring system blended with ML results and business rules, need to have a balanced approach for scoring.
  • Pre-set business targets, flexibility of code and continuously testing can maximize the usage of the engine.
  • Platform, Integration, and the change of way of work matter

Add comment

Highlight option

Turn on the "highlight" option for any widget, to get an alternative styling like this. You can change the colors for highlighted widgets in the theme options. See more examples below.


Instagram has returned empty data. Please authorize your Instagram account in the plugin settings .

Ivana Kotorchevikj

Categories count color


Small ads


  • Traffic lights
  • WoMo
  • Setra presentation
  • It never ends
  • stand still screening-smoking girl
  • Maria d'Odessa performs her art of make-up
  • Afro-deko-mono
  • Maria d'Odessa, touching
  • Maria d'Odessa au bâton de rouge-baiser

Social Widget

Collaboratively harness market-driven processes whereas resource-leveling internal or "organic" sources.