Feedback

Faculté des Sciences appliquées
Faculté des Sciences appliquées
MASTER THESIS
VIEW 95 | DOWNLOAD 0

Machine Learning Applied to Music: Prediction of the Popularity of a Track

Download
Benzerga, Amina ULiège
Promotor(s) : Geurts, Pierre ULiège
Date of defense : 25-Jun-2018/26-Jun-2018 • Permalink : http://hdl.handle.net/2268.2/4606
Details
Title : Machine Learning Applied to Music: Prediction of the Popularity of a Track
Translated title : [fr] L’apprentissage automatique appliqué à la musique: prédiction de la popularité de chansons
Author : Benzerga, Amina ULiège
Date of defense  : 25-Jun-2018/26-Jun-2018
Advisor(s) : Geurts, Pierre ULiège
Committee's member(s) : Embrechts, Jean-Jacques ULiège
Louppe, Gilles ULiège
Lidy, Thomas 
Language : English
Number of pages : 101
Keywords : [en] machine learning
[en] time series
[en] forecasting
Discipline(s) : Engineering, computing & technology > Computer science
Target public : Other
Institution(s) : Université de Liège, Liège, Belgique
Degree: Master en ingénieur civil en informatique, à finalité spécialisée en "intelligent systems"
Faculty: Master thesis of the Faculté des Sciences appliquées

Abstract

[en] Machine learning applied to music. We tried, in this thesis, to predict the popularity of tracks. To do so, we used time series forecasting models as well as neural networks and random forest.


File(s)

Document(s)

File
Access TFE_résumé.pdf
Description:
Size: 101.3 kB
Format: Adobe PDF
File
Access master-thesis-popularity.pdf
Description:
Size: 8.04 MB
Format: Adobe PDF

Annexe(s)

File
Access MAE_comp_c_test_hist.png
Description: MAE obtained for the test set for LSTM models
Size: 76.15 kB
Format: image/png
File
Access p_vs_a.png
Description: Comparing the number of tracks for which each model performs better than the others.
Size: 15 kB
Format: image/png
File
Access pred_1.png
Description: Forecasts obtained using our models are compared to the real values
Size: 107.68 kB
Format: image/png
File
Access pred_2.png
Description: Forecasts obtained using our models are compared to the real values
Size: 96.03 kB
Format: image/png
File
Access rf_importance.png
Description: Relevant audio features for predicting the trend of a track, only using the audio features
Size: 109.97 kB
Format: image/png

Author

  • Benzerga, Amina ULiège Université de Liège > Master ingé. civ. info., à fin.

Promotor(s)

Committee's member(s)

  • Embrechts, Jean-Jacques ULiège Université de Liège - ULiège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Techniques du son et de l'image
    ORBi View his publications on ORBi
  • Louppe, Gilles ULiège Université de Liège - ULiège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Big Data
    ORBi View his publications on ORBi
  • Lidy, Thomas Musimap > Head of machine learning
  • Total number of views 95
  • Total number of downloads 0










All documents available on MatheO are protected by copyright and subject to the usual rules for fair use.
The University of Liège does not guarantee the scientific quality of these students' works or the accuracy of all the information they contain.