Nowadays, music aficionados generate millions of listening events every day and share them via platforms such as Spotify, Last.fm, or Twitter. In 2016, the LFM-1b dataset (http://www.cp.jku.at/datasets/LFM-1b) containing more than 1 billion listening events of about 120,000 Last.fm users has been released to the research community and interested public. Since then, we performed various data analysis and machine learning tasks on these large amounts of user and listening data. The gained insights helped to develop new listener models and integrate them into music recommender systems, in an effort to increase personalization of the recommendations.

In this talk, I will report on our experiments with the LFM-1b dataset, focusing on the following topics:

- analyzing music taste around the world and clustering on the country level

- quantifying listener and country mainstreaminess

- music recommendation tailored to listener characteristics

- predicting user characteristics from music listening habits

- predicting country-specific genre preferences from cultural and socio-economic factors