Big data visual exploration is believed to be considered as a recommendation problem. This proximity concerns essentially their purpose: it consists in selecting among huge amount of data those that are the most valuable according to specific criteria, to eventually present it to users. On the other hand, the recommendation systems are recently resolved mostly using neural networks (NNs). The present paper proposes three alternative solutions to improve the big data visual exploration based on recommendation using matrix factorisation (MF) namely: conventional, alternating least squares (ALS)-based and NN-based methods. It concerns generating the implicit data used to build recommendations, and providing the most valuable data patterns according to the user profiles. The first two solutions are developed using Apache Spark, while the third one was developed using TensorFlow2. A comparison based on results is done to show the most efficient one. The results show their applicability and effectiveness.
الكلمات المفتاحية :
Big data visualisation
Recommendation systems
Collaborative filtering
Content-based filtering
Matrix factorisation
Alternating least square
Machine learning
Neural networks.
M. S. Kahil, A. Bouramoul and M. Derdour. 2023. Big data visual exploration as a recommendation problem. Int. J. Data Min. Model. Manag., 15, 2 (June 2023), Inderscience Publishers Ltd, 133-153. DOI: https://doi.org/10.1504/IJDMMM.2023.131378.
APA :
Kahil, M. S., Bouramoul, A. & Derdour, M. (2023, June). Big data visual exploration as a recommendation problem. Int. J. Data Min. Model. Manag., 15(2), Inderscience Publishers Ltd, 133-153. DOI: https://doi.org/10.1504/IJDMMM.2023.131378
IEEE :
M. S. Kahil, A. Bouramoul and M. Derdour, "Big data visual exploration as a recommendation problem". Int. J. Data Min. Model. Manag., vol. 15, no. 2, Inderscience Publishers Ltd, pp. 133-153, June, 2023. DOI: https://doi.org/10.1504/IJDMMM.2023.131378.
BibTeX :
@article{misc-lab-430, author = {Kahil, Moustafa Sadek and Bouramoul, Abdelkrim and Derdour, Makhlouf}, title = {Big data visual exploration as a recommendation problem}, journal = {Int. J. Data Min. Model. Manag.}, volume = {15}, number = {2}, issn = {1759-1163}, pages = {133--153}, publisher = {Inderscience Publishers Ltd}, year = {2023}, month = {June}, doi = {10.1504/IJDMMM.2023.131378}, url = {https://doi.org/10.1504/IJDMMM.2023.131378}, keywords = {big data visualisation, recommendation systems, collaborative filtering, content-based filtering, matrix factorisation, alternating least square, machine learning, neural networks.} }
RIS :
TI - Big data visual exploration as a recommendation problem AU - M. S. Kahil AU - A. Bouramoul AU - M. Derdour PY - 2023 SN - 1759-1163 JO - Int. J. Data Min. Model. Manag. VL - 15 IS - 2 SP - 133 EP - 153 PB - Inderscience Publishers Ltd AB - Big data visual exploration is believed to be considered as a recommendation problem. This proximity concerns essentially their purpose: it consists in selecting among huge amount of data those that are the most valuable according to specific criteria, to eventually present it to users. On the other hand, the recommendation systems are recently resolved mostly using neural networks (NNs). The present paper proposes three alternative solutions to improve the big data visual exploration based on recommendation using matrix factorisation (MF) namely: conventional, alternating least squares (ALS)-based and NN-based methods. It concerns generating the implicit data used to build recommendations, and providing the most valuable data patterns according to the user profiles. The first two solutions are developed using Apache Spark, while the third one was developed using TensorFlow2. A comparison based on results is done to show the most efficient one. The results show their applicability and effectiveness. KW - big data visualisation KW - recommendation systems KW - collaborative filtering KW - content-based filtering KW - matrix factorisation KW - alternating least square KW - machine learning KW - neural networks. DO - 10.1504/IJDMMM.2023.131378 UR - https://doi.org/10.1504/IJDMMM.2023.131378 ID - misc-lab-430 ER -