ATTENTION/WARNING - NE PAS DÉPOSER ICI/DO NOT SUBMIT HERE

Ceci est la version de TEST de DIAL.mem. Veuillez ne pas soumettre votre mémoire sur ce site mais bien à l'URL suivante: 'https://thesis.dial.uclouvain.be'.
This is the TEST version of DIAL.mem. Please use the following URL to submit your master thesis: 'https://thesis.dial.uclouvain.be'.
 

Next Point-of-interest prediction : towards an interpretable model

Mulamba Ke Tchomba, Maxime
(2019)

Files

Mulamba_77811400_2019.pdf
  • Closed access
  • Adobe PDF
  • 1.01 MB
Download not available
Mulamba_77811400_2019_Appendix1.zip
  • Closed access
  • Unknown
  • 178.3 MB
Download not available

Details

Supervisors
Nijssen, Siegfried
Faculty
Ecole polytechnique de Louvain
Degree label
Master [120] en sciences informatiques
Abstract
State-of-the art models for the Next Location Prediction Problem rely on sophisticated techniques such as Matrix Factorization or Artificial Neural Networks to tackle this task, neglecting interpretability for performance. In this paper, we analyze STRNN, a model based on Recurrent Neural Network and exploit spatial, temporal and sequential influences to accurately predict the next location. We propose an original model, STILP, a white-box alternative which aims to solve the next location problem in a similar manner.

Citations

  • APA

Mulamba Ke Tchomba, M. (2019). Next Point-of-interest prediction : towards an interpretable model. https://dial-mem.test.bib.ucl.ac.be/handle/2078.2/17552