Diploma thesis deals with fighting insurance fraud from the very beginning to the end, seen from insurance company's perspective. It also tries to see insurance frauds and dealing with them not only from IT point of view, but also accompany other department's views and needs. It's starting with organizational overview and its readiness to fight fraud and trying to show, how to improve. Furthermore it introduces reader with basic terms and phrases of insurance fraud and continues with general description of this encounter. It continues with indicators of insurance fraud and its examples and strategies, how to find them in data. Next part of my thesis is focusing on available external sources and possible insurance companies' cooperation, for maximized ability to detect suspicious cases. This is continued by selection of proper system, requirements definition and its goals. Last part shows one of FMS solutions and its description, from requirements up to complete solutions architecture and screenshots of given system.

This thesis aims to identify and evaluate the risks related to payment cards and their use. The main focus is the methods used to commit card related fraud and possible methods of protection related to this topic. First of all, the technology that is nowadays used in relation with the payment cards is analyzed and its weaknesses and attacks used to gather card information are described. After that, statistical data related to card fraud are analyzed in relation with different world regions. Qualitative analysis of risk related to payment card use is performed on the statistical data of ECB for the cards issued in Czech Republic. The qualitative analysis is then followed by recommendations that are designed to limit the risk's impact or probability. To verify the recommendations, a survey is carried out.

This thesis is focused on theme of insurance´s fraud, primarily from the legal aspects. The thesis consist of legislative of insurance fraud according to the Criminal Code, also including a list of punishment. The following part dedicate to active insurers fight against cheats, their investigation and using more effective instruments and measures of their prevention. The thesis doesn´t forget statistical data and development in detection of insurance fraud in last 5 years. There is also the judicature of High Court and the examples of practise.

Subsidy fraud and damaging the financial interests of the European union (Section 260 of the Penal Code) Abstract This thesis is focused on Czech and European legal framework of fight against subsidy fraud. The thesis also focuses on practices and general concepts of institutions which are tasked with fighting fraudulent conducts. The method of processing is mainly analysis and description. The thesis is structured in three parts. The first part brings attention to the characteristics of subsidy fraud as codified in section 212 of the Czech penal code. The chapter includes authors' suggestions of changes to the section 212. The second part presents analysis of crime of damaging the financial interests of the European union as codified in section 260 of the Czech penal code. The chapter includes authors' suggestions of changes to the section 260. After that international and European legal framework, which represents foundation of Czech legal framework, is thoroughly observed. The thesis explores the history of fight against fraud in the European union and its predecessors from the beginning to current days. Further attention is brought on European institutions tasked with fight against fraud, specifically European Public Prosecutor's Office and European Anti-Fraud Office. Possible weaknesses in the concept...

This thesis deals with fraud detection in a real-world environment with datasets coming from Svenska Handelsbanken. The goal was to investigate how well machine learning can classify fraudulent transactions and how new additional features affected classification. The models used were EFSVM, RUTSVM, CS-SVM, ELM, MLP, Decision Tree, Extra Trees, and Random Forests. To determine the best results the Mathew Correlation Coefficient was used as performance metric, which has been shown to have a medium bias for imbalanced datasets. Each model could deal with high imbalanced datasets which is common for fraud detection. Best results were achieved with Random Forest and Extra Trees. The best scores were around 0.4 for the real-world datasets, though the score itself says nothing as it is more a testimony to the dataset’s separability. These scores were obtained when using aggregated features and not the standard raw dataset. The performance measure recall’s scores were around 0.88-0.93 with an increase in precision by 34.4%-67%, resulting in a large decrease of False Positives. Evaluation results showed a great difference compared to test-runs, either substantial increase or decrease. Two theories as to why are discussed, a great distribution change in the evaluation set, and the sample size increase (100%) for evaluation could have lead to the tests not being well representing of the performance. Feature aggregation were a central topic of this thesis, with the main focus on behaviour features which can describe patterns and habits of customers. For these there were five categories: Sender’s fraud history, Sender’s transaction history, Sender’s time transaction history, Sender’shistory to receiver, and receiver’s history. Out of these, the best performance increase was from the first which gave the top score, the other datasets did not show as much potential, with mostn ot increasing the results. Further studies need to be done before discarding these features, to be certain they don’t improve performance. Together with the data aggregation, a tool (t-SNE) to visualize high dimension data was usedto great success. With it an early understanding of what to expect from newly added features would bring to classification. For the best dataset it could be seen that a new sub-cluster of transactions had been created, leading to the belief that classification scores could improve, whichthey did. Feature selection and PCA-reduction techniques were also studied and PCA showedgood results and increased performance. Feature selection had not conclusive improvements. Over- and under-sampling were used and neither improved the scores, though undersampling could maintain the results which is interesting when increasing the dataset. / Denna avhandling handlar om upptäcka bedrägerier i en real-world miljö med data från Svenska Handelsbanken. Målet var att undersöka hur bra maskininlärning är på att klassificera bedrägliga transaktioner, och hur nya attributer hjälper klassificeringen. Metoderna som användes var EFSVM, RUTSVM, CS-SVM, ELM, MLP, Decision Tree, Extra Trees och Random Forests. För evaluering av resultat används Mathew Correlation Coefficient, vilket har visat sig ha småttt beroende med hänsyn till obalanserade datamängder. Varje modell har inbygda värden för attklara av att bearbeta med obalanserade datamängder, vilket är viktigt för att upptäcka bedrägerier. Resultatmässigt visade det sig att Random Forest och Extra Trees var bäst, utan att göra p-test:s, detta på grund att dataseten var relativt sätt små, vilket gör att små skillnader i resultat ej är säkra. De högsta resultaten var cirka 0.4, det absoluta värdet säger ingenting mer än som en indikation om graden av separation mellan klasserna. De bäst resultaten ficks när nya aggregerade attributer användes och inte standard datasetet. Dessa resultat hade recall värden av 0,88-0,93 och för dessa kunde det synas precision ökade med 34,4% - 67%, vilket ger en stor minskning av False Positives. Evluation-resultaten hade stor skillnad mot test-resultaten, denna skillnad hade antingen en betydande ökning eller minskning. Två anledningar om varför diskuterades, förändring av evaluation-datan mot test-datan eller att storleksökning (100%) för evaluation har lett till att testerna inte var representativa. Attribute-aggregering var ett centralt ämne, med fokus på beteende-mönster för att beskriva kunders vanor. För dessa fanns det fem kategorier: Avsändarens bedrägerihistorik, Avsändarens transaktionshistorik, Avsändarens historik av tid för transaktion, Avsändarens historik till mottagaren och mottagarens historik. Av dessa var den största prestationsökningen från bedrägerihistorik, de andra attributerna hade inte lika positiva resultat, de flesta ökade inte resultaten.Ytterligare mer omfattande studier måste göras innan dessa attributer kan sägas vara givande eller ogivande. Tillsammans med data-aggregering användes t-SNE för att visualisera högdimensionsdata med framgång. Med t-SNE kan en tidig förståelse för vad man kan förvänta sig av tillagda attributer, inom klassificering. För det bästa dataset kan man se att ett nytt kluster som hade skapats, vilket kan tolkas som datan var mer beskrivande. Där förväntades också resultaten förbättras, vilket de gjorde. Val av attributer och PCA-dimensions reducering studerades och PCA-visadeförbättring av resultaten. Over- och under-sampling testades och kunde ej förbättrade resultaten, även om undersampling kunde bibehålla resultated vilket är intressant om datamängden ökar.

>Magister Scientiae - MSc / The recent years have seen an increase in the number of users accessing online services using communication devices such as computers, mobile phones and cards based credentials such as credit cards. This has prompted most governments and business organizations to change the way they do business and manage their identity information. The coming of the online services has however made most Internet users vulnerable to identity fraud and theft. This has resulted in a subsequent increase in the number of reported cases of identity theft and fraud, which is on the increase and costing the global industry excessive amounts. Today with more powerful and effective technologies such as artificial intelligence, wireless communication, mobile storage devices and biometrics, it should be possible to come up with a more effective multi-modal authentication system to help reduce the cases of identity fraud and theft. A multi-modal digital identity management system IS proposed as a solution for managing digital identity information in an effort to reduce the cases of identity fraud and theft seen on most online services today. The proposed system thus uses technologies such as artificial intelligence and biometrics on the current unsecured networks to maintain the security and privacy of users and service providers in a transparent, reliable and efficient way. In order to be authenticated in the proposed multi-modal authentication system, a user is required to submit more than one credential attribute. An artificial intelligent technology is used to implement a technique of information fusion to combine the user's credential attributes for optimum recognition. The information fusion engine is then used to implement the required multi-modal authentication system.

International Revenue Sharing Fraud (IRSF) is one of the most persistent types of fraud within the telecommunications industry. According to the 2017 Communications Fraud Control Association (CFCA) fraud loss survey, IRSF costs 6 billion dollars a year. Therefore, the detection of such frauds is of vital importance to avoid further loss. Though many efforts have been made, very few utilize the temporal patterns of phone call traffic. This project, supported with Sinch’s real production data, aims to exploit both spatial and temporal patterns learned by Graph Attention Neural network (GAT) with Gated Recurrent Unit (GRU) to find suspicious timestamps in the historical traffic. Moreover, combining with the time-independent Isolation forest model, our model should give better results for the phone call records. This report first explains the mechanism of IRSF in detail and introduces the models that are applied in this project, including GAT, GRU, and Isolation forest. Finally, it presents how our experiments have been conducted and the results with extensive analysis. Moreover, we have achieved 42.4% precision and 96.1% recall on the test data provided by Sinch, showing significant advantages over both previous work and baselines. / International Revenue Sharing Fraud (IRSF) är en av de mest ihållande typerna av bedrägerier inom telekommunikationsindustrin. Enligt 2017 Communications Fraud Control Association (CFCA) bedrägeriförlustundersökning kostar IRSF 6 miljarder dollar per år. Därför är upptäckten av sådana bedrägerier av avgörande betydelse för att undvika ytterligare förluster. Även om många ansträngningar har gjorts är det väldigt få som använder telefonsamtalstrafikens tidsmässiga mönster. Detta projekt, med stöd av Sinchs verkliga produktionsdata, syftar till att utnyttja både rumsliga och tidsmässiga mönster som lärts in av Graph Attention Neural Network (GAT) med Gated Recurrent Unit (GRU) för att hitta misstänkt tid i den historiska trafiken. Dessutom, i kombination med den tidsoberoende skogsmodellen Isolation, borde vår modell ge bättre resultat för telefonsamtalsposterna. Denna rapport förklarar först mekanismen för IRSF i detalj och introducerar modellerna som används i detta projekt, inklusive GAT, GRU och Isolation forest. Slutligen presenteras hur våra experiment har genomförts och resultaten med omfattande analys. Dessutom har vi uppnått 42.4% precision och 96.1% återkallelse på testdata från Sinch, vilket visar betydande fördelar jämfört med både tidigare arbete och baslinjer.

The economic prosperity of the late 1990s was characterized by a perceived expansive growth that increased the expectations of a company's performance. WorldCom, a telecommunications company, was a victim of these expectations that led to the evolution of a fraud designed to deceive the public until the economic outlook improved. Through understanding what led to the fraud, how the fraud grew, and what its effects were, lessons can be derived to gain a better understanding of the reasons behind a fraud and to prevent future frauds from occurring or growing as big as the WorldCom fraud did.

Today, the use of one's bank card to pay or withdraw money is common. Modern technology provides us with the convenience of instant transactions at the automated teller machine or point of sale but unfortunately, it has also brought the reality and risk of card skimming and counterfeit card fraud. Criminals have become very efficient and technologically advanced in skimming and counterfeiting cards, to such an extent that counterfeit card fraud has become a significant threat to the public, banking, retail and business in South Africa. Counterfeit card fraud is a complex, multi-faceted crime, requiring specific skills and knowledge of card counterfeiting methods from police and bank investigators. The scope of its investigation is wide. It includes different crime scenes and offenders, sophisticated equipment and various aspects that need to be identified positively. Investigators find it difficult to identify perpetrators and certain aspects unique to this crime and, as a result, many investigations are unsuccessful. This research endeavours to establish what identification methods are available to investigators and which are effective. / Police Practice / M. Tech. (Forensic Investigation)

The use of credit cards has become a way of life in many parts of the world. Credit cards have also created many new opportunities for criminal activity. It is in this light that organizations such as VISA International have explored a variety of security alternatives by constantly reviewing security measures that may be applied to cards and devote considerable resources to the maintenance of security systems and programmes. These programmes mandated by the association, include uniform card standards, security standards for manufactures, embossing and encoding of cards, standards for mailing the cards and credit background investigations of applicants. These standards assist investigators in examining counterfeit cards and distinguish a counterfeit card from a genuine card. The constant reviewing of security features and methods by the association is to create a card that is technically difficult to alter or counterfeit. / Criminology / M.Tech. (Forensic Investigation)