Game Intelligent Analyst - Anomaly Detection in Casino Games using Machine Learning Algorithms
Merchie, Florian
Promoteur(s) : Wehenkel, Louis ; Boniver, Christophe
Date de soutenance : 25-jui-2018/26-jui-2018 • URL permanente : http://hdl.handle.net/2268.2/4651
Détails
Titre : | Game Intelligent Analyst - Anomaly Detection in Casino Games using Machine Learning Algorithms |
Titre traduit : | [fr] Détection d'anomalies dans les jeux de casino par algorithmes d'apprentissage inductif |
Auteur : | Merchie, Florian |
Date de soutenance : | 25-jui-2018/26-jui-2018 |
Promoteur(s) : | Wehenkel, Louis
Boniver, Christophe |
Membre(s) du jury : | Geurts, Pierre
Louppe, Gilles Boniver, Aurélie |
Langue : | Anglais |
Nombre de pages : | 75 |
Mots-clés : | [en] machine learning [en] casino [en] extra trees [en] supervised learning [en] anomaly detection [en] density ratio |
Discipline(s) : | Ingénierie, informatique & technologie > Sciences informatiques |
Public cible : | Professionnels du domaine Etudiants |
Institution(s) : | Université de Liège, Liège, Belgique |
Diplôme : | Master en ingénieur civil en informatique, à finalité spécialisée en "intelligent systems" |
Faculté : | Mémoires de la Faculté des Sciences appliquées |
Résumé
[en] Anomaly detection is a very large and complex field. In recent years, several
techniques based on data science were designed in order to improve the efficiency of
methods developed for this purpose. In particular, density-based anomaly detection
allows to estimate how much probability densities differ from each other by solving
a supervised learning problem using data drawn from these densities as a dataset.
Besides, the casino games company GAMING1 aims at automating the detection of
behavior modifications in its games when an update is performed. This master thesis introduces a method based on density-based anomaly detection to reach GAMING1’s objective. We explore two main approaches to solve this problem. The first
one relies on standard supervised learning algorithms. For this approach, two algorithms were considered: Extremely randomized trees and linear support vector machine. The second approach is based on deep learning and exploits recurrent neural
networks architectures. Using experimental cases of anomalies in casino games, it’s
been shown that extremely randomized trees outperforms both other methods as
far as performances and visual interpretation are concerned, but also considering
computational resources. In addition to accuracy, we rely on several other metrics
related to the comparison of probability densities in order to assess formal performances of the presented algorithm. We show that the tree-based method allows us
to distinguish irregular data with an accuracy of at least 0.7 for standard anomalies,
while providing relevant visual support thanks to probability densities representation. Moreover, it’s also possible to identify more hardly detectable anomalies by
using classifier calibration in order to enhance the visual support of the probability
densities, despite an associated low accuracy.
Fichier(s)
Document(s)
Annexe(s)
Description: LaTeX source code of the master thesis
Taille: 4.68 MB
Format: Unknown
Citer ce mémoire
L'Université de Liège ne garantit pas la qualité scientifique de ces travaux d'étudiants ni l'exactitude de l'ensemble des informations qu'ils contiennent.