Fair Averages: Bayesian Ratings for Products with Few Reviews
This lesson is part of the course
In this lesson
You calculate the catalogue's weighted average rating, give every product a fair (Bayesian) average that pulls small samples towards it, and compare the ranking by raw average with the ranking by fair average.
Buy the course once for $9.99 to unlock every lesson and lab, the final exam and the certificate – lifetime access, no subscription.
Lessons in this course
- Star Distributions: Counts per Star, Shares, Mean vs Median Locked
- Fair Averages: Bayesian Ratings for Products with Few Reviews Locked
- Confidence-Adjusted Rankings: the Wilson Lower Bound for Positive Shares Locked
- Review Velocity: Reviews per Week, Trend and Days Since the Last Review Locked
- Themes from Review Text: Keyword Flags, Stars per Theme and Complaint Shares Locked
- Response Management: Response Times, Response Rates and the Median Locked
- Rating vs Sales: Conversion by Rating Band and What a Star Might Be Worth Locked
- Capstone: Reputation Dashboard with Fair Ratings, Response Rates and Traffic Lights Locked