Course recap

PySpark で作る Recommendation Engines

Jamen Long

Data Scientist at Nike

Course summary

Three types of data
  • Explicit Ratings
  • Implicit Ratings using user behavior counts
  • Implicit Ratings using binary user behavior
PySpark で作る Recommendation Engines

Things to bear in mind

  • The more data the better
PySpark で作る Recommendation Engines

Things to bear in mind (cont.)

  • The more data the better
  • The best model evaluation is whether actual users take your recommendations
PySpark で作る Recommendation Engines

Resources

PySpark で作る Recommendation Engines

Let's practice!

PySpark で作る Recommendation Engines

Preparing Video For Download...