Porsche adds a recommendation system to its car configurator
Porsche announced in a press release that Porsche has added a recommendation function to its Car Configurator. Porsche claims to have trained 270 neural networks on several million data points and they report an astonishing 90% accuracy. I am not sure though, how accuracy was calculated exactly.
A user can start the recommendation engine by clicking on the light-bulb icon.
This opens a right-hand panel with suggested items to add to the configuration.
This list differs based on the previously chosen options. For instance, in the example above, I get recommendations for Adaptive Sports Seats on the top position with an 87% configuration match (whatever that means). On the second position, 20″/21″ 911 Turbo S Wheels are recommended (80% match).
However, when changing the car colour from white to red, the recommended items change.
The top recommendation remains the same (Adaptive Car Seats) but on second position now is the Electric Slide/Tilt Sunroof.
Apple introduces Fitness+, a “new engaging and personalized fitness experience”
Google Assistant app now uses your searches to make personalized recommendations [Sarah Perez @ TechCrunch]
Google Podcast gets Personalized Audio News Recommendations [Liz Gannes @ Google]
About The Author
Joeran Beel
I am the founder of Recommender-Systems.com and head of the Intelligent Systems Group (ISG) at the University of Siegen, Germany https://isg.beel.org. We conduct research in recommender-systems (RecSys), personalization and information retrieval (IR) as well as on automated machine learning (AutoML), meta-learning and algorithm selection. Domains we are particularly interested in include smart places, eHealth, manufacturing (industry 4.0), mobility, visual computing, and digital libraries. We founded or maintain, among others, LensKit-Auto, Darwin & Goliath, Mr. DLib, and Docear, each with thousand of users; we contributed to TensorFlow, JabRef and others; and we developed the first prototypes of automated recommender systems (AutoSurprise and Auto-CaseRec) and Federated Meta Learning (FMLearn Server and Client).