Author Archive | Lewis Perdue

Machine Learning + Big Data + Tribes = Happier Consumers & Fewer Regulation Hassles

Complaints about the use of personal information for everything from predictive product recommendations to credit ratings and consumer credit card interest rates have provoked lawsuits,  increasing consumer outrage,  and a growing chorus of demands for tighter governmental controls. The greater accuracy of the Tribes algorithm plus its ability to perform in a totally anonymous data […]

Next Glass: A Step In Solving Wine Rating’s Genetic Issues

NOTE: This article uses “wine” to avoid having to type “beer or wine” everywhere. But, unless noted otherwise, a reference to wine refers to both beer and wine. The Next Glass wine and beer selection app is a step toward more accurate wine recommendations, but faces several substantial hurdles on the path to accuracy, scalability […]

How Predictive Big Data Fails

Recommendations from big data predictive methods are a lot like the use of epidemiology to determine the cause of a disease: Both rely on the statistical analysis and correlation of massive amounts of data. Both are indicative that something is happening. Both can offer insights into a phenomenon. Both are easily derailed by unknown confounding […]

Recommendation News – Nov. 3, 2014

Corkz Update Extends Global Reach of the Wine Information App Pandora for beer? Vivino, Club W Use Tech To Help Wine Lovers Find Favorites Damned Experts! Damned “Know-Nothings!” … (Damn You, Consumers) Grade Inflation Is Killing The Value of Wine Reviews Discovering your own taste in wine beyond 100-point scores What’s 97 points between friends? […]

What Problems Does Tribes/Clans Solve & How?

The Tribes algorithm offers far more accurate recommendations than any other system in use for products and services “of personal taste” including (but not limited to): books, movies, wine, restaurants, cheese, beer, cocktails, and anything “Yelp-able.” Because wine is probably the most complicated product on the planet to recommend accurately, Tribes has been developed through […]

INCOMPATIBILITY: Profile Matching

A PERSONAL NOTE: My apologies in advance to a number of good friends and colleagues who are still trying to get wine profile systems to work. But, as you read on, my hands-on experience and further research leads me to believe that the system has inherent problems that will prevent it from reaching the potential […]

THE PROBLEM: Casino Recommendations

This is part of a series on flaws in current wine recommendation systems originally published at Wine Industry Insights: Genetics: Inherited Taste Chaos Sabotages How Wine Gets Recommended Scaling: 3/4 Of Wine In The US Has NEVER Been Rated By Critics Misinterpretation: Words: Big Trouble For Tasting Notes Inconsistency: Rating The Rating Systems Psychology: Vino-Anxiety, […]