01_​LastFM_​Recommendations

0 ×

This workflow takes social media data from a popular music site and uses predictive analytics to make music preference recommendations for the top artists. In addition, the workflow creates a multimedia report that shows the top artists and the other musicians associated with each in the form “Others who like X also like….”. We do this by performing an advanced association analysis and utilizing the resulting statistics to select lists of artists and recommendations. We then combine this list with overall facts about the sample and enhance the artist data with pictures to create a dynamic multi-media report. The dataset contains social networking, tagging, and music artist listening information from a set of 2K users from Last.fm online music system (http://www.last.fm).

Nodes

• GroupBy4 ×
• Data to Report (BIRT)3 ×
• File Reader2 ×
• Joiner2 ×
• Sorter2 ×
• Show all 10 nodes

Extensions

• FeatureKNIME Base nodes
• FeatureKNIME Itemset Mining
• FeatureKNIME Math Expression (JEP)
• FeatureKNIME Reporting Runtime (BIRT)

Links

• Last.fm

  http://www.last.fm
• Recommendation Engine for Retailers

  www.knime.com/recommendation-engine-for-retailers
• Social Media Music Recommendation

  www.knime.com/knime-applications/lastfm-recommodation