Background: Detecting anomalies in time-series data is a task that can be done with the help of data driven machine learning models. This thesis will investigate if, and how well, different machine learning models, with an unsupervised approach,can detect anomalies in the e-Transaction system Ericsson Wallet Platform. The anomalies in our domain context is delays on the system. Objectives: The objectives of this thesis work is to compare four different machine learning models ,in order to find the most relevant model. The best performing models are decided by the evaluation metric F1-score. An intersection of the best models are also being evaluated in order to decrease the number of False positives in order to make the model more precise. Methods: Investigating a relevant time-series data sample with 10-minutes interval data points from the Ericsson Wallet Platform was used. A number of steps were taken such as, handling data, pre-processing, normalization, training and evaluation.Two relevant features was trained separately as one-dimensional data sets. The two features that are relevant when finding delays in the system which was used in this thesis is the Mean wait (ms) and the feature Mean * N were the N is equal to the Number of calls to the system. The evaluation metrics that was used are True positives, True Negatives, False positives, False Negatives, Accuracy, Precision, Recall, F1-score and Jaccard index. The Jaccard index is a metric which will reveal how similar each algorithm are at their detection. Since the detection are binary, it’s classifying the each data point in the time-series data. Results: The results reveals the two best performing models regards to the F1-score.The intersection evaluation reveals if and how well a combination of the two best performing models can reduce the number of False positives. Conclusions: The conclusion to this work is that some algorithms perform better than others. It is a proof of concept that such classification algorithms can separate normal from non-normal behavior in the domain of the Ericsson Wallet Platform.

No description available.

In recent years, blockchain has received more attention in different areas wheredifferent chains show unique properties. Society has been strongly affected by thegrowth of technology and digitalization. Despite the success, the banking system is ina stagnant state in the development of the transaction system. Smart contracts havemore significant potential to be used against blockchain. The contract does not requiremanual handling but could operate independently during all hours of the day. Inaddition, limit them by being applied solely to enable an overview of completedtransactions. A challenge seen with implementing the technology from the bank'sperspective is a new type of form of cooperation. If Ethereum succeeds in proving itselfin its Proof of stake model, there is great potential for a more significant part of thebanking industry to start using smart contracts. The purpose of the study was toinvestigate the effects of implementing smart contracts in a dynamic transaction systemover time. Data obtained from interviews and literature study was the basis formodeling the system. The study aimed to carry out simulations to then be able toevaluate the effects. According to the interviews, blockchain is seen more as a tool tosolve particular problems. The simulations show how the entities in the system areaffected over time when the technology smart contracts are applied.

Cette thèse vise à identifier les contraintes institutionnelles et réglementaires qui limitent le développement des unités informelles à Djibouti en faisant à la fois une analyse microéconomique et macroéconomique. L’examen des institutions montre que des habitudes (corruption, passe droit) en matière de règlement de l’administration créent des coûts de transaction et obligent les micro-entreprises à se réfugier dans le secteur informel. Un modèle de régression montre que la qualité de la justice (mesurée par l’indicateur de Rule of Law de la Banque mondiale) est une variable déterminante pour expliquer le poids de l’économie non observée et donc celui du secteur informel, dans le PIB officiel. La dynamique des micro-entreprises est appréhendée à partir de 2 enquêtes (2001 et 2005) portant sur le même échantillon. L’analyse de la mobilité à l’aide de matrices de transition révèle l’existence non pas d’un seul seuil infranchissable, mais plutôt de trois (1 actif, 2-5 actifs, 6-9 actifs et 10 actifs et plus) et confirme la thèse du «missing-middle». L’analyse factorielle discriminante indique que la légalité est une variable déterminante pour expliquer le blocage apparent des micro-entreprises au-delà de 6 à 9 actifs. Enfin, l’enquête 2007 sur les activités de transfert d’argents (hawalas) montre leur impact important sur le plan macroéconomique ; elle suggère la prise en compte de la spécificité et de l’utilité de ces institutions comme un dispositif complémentaire aux banques dont l’intégration dans le système financier formel devrait être facilitée. / This research seeks to detect the institutional and regulatory constraints that limit the development of informal units in Djibouti by both the macroeconomic and microeconomic analysis. The review shows that institutional habits (corruption, going right) in regulation created transaction costs and force small businesses to take refuge in the informal sector. A regression model shows that the quality of justice (as measured by this indicator of Rule of Law of the World Bank) is a determining variable in explaining the weight of the non-observed economy and hence the informal sector in GDP official. The dynamics of micro-enterprises is approached from 2 surveys (2001 and 2005) on the same sample. The analysis of mobility through transition matrices reveals the existence of three thresholds (1 employee, 2-5 employees, 6-9 employees and 10 employees and more) and not only one single threshold, albeit it confirms the thesis of «missing-middle». The discriminating factor analysis indicates that the law is a crucial variable that explains the apparent blocking of micro-enterprises beyond 6 to 9 employees. Finally, the 2007 survey on the money transfer activities (hawalas) shows that these institutions have a significant impact on the macroeconomic level and suggests that their usefulness and specificity should be taken into account in order to integrate this banking device within the formal financial system.