Music Data YearPredictionMSD Task
Jump to navigation
Jump to search
A Music Data YearPredictionMSD Task is a fully-supervised univariate point estimation task that predicts year for a music record.
- Context:
- It is assocatied with a YearPredictionMSD numeric-predictors regression dataset, e.g. at [1]
- Example(s):
- Counter-Example(s):
- See: Bike Sharing Service, Sensor Network.
References
2011
- http://archive.ics.uci.edu/ml/datasets/YearPredictionMSD
- QUOTE: Abstract: Prediction of the release year of a song from audio features. Songs are mostly western, commercial tracks ranging from 1922 to 2011, with a peak in the year 2000s.
- Data Set Characteristics: Multivariate
- Number of Instances: 515345
- Attribute Characteristics: Real
- Number of Attributes: 90
- Date Donated: 2011-02-07
- Associated Tasks: Regression
- Source: This data is a subset of the Million Song Dataset: http://labrosa.ee.columbia.edu/millionsong/ a collaboration between LabROSA (Columbia University) and The Echo Nest. Prepared by T. Bertin-Mahieux <tb2332 '@' columbia.edu>
- Data Set Information: You should respect the following train / test split:
train: first 463,715 examples .
test: last 51,630 examples
It avoids the 'producer effect' by making sure no song from a given artist ends up in both the train and test set.
- QUOTE: Abstract: Prediction of the release year of a song from audio features. Songs are mostly western, commercial tracks ranging from 1922 to 2011, with a peak in the year 2000s.