Banks and other financial institutions are to a certain extent obligated to ensure that their services are not utilized for any type of financial crime. This thesis investigates the possibility of analyzing bank customers' transactional behaviour with machine learning to detect if they are involved in financial crime. The purpose of this is to see if a new approach to processing and analyzing transaction data could make financial crime detection more accurate and efficient. Transactions of a customer over a time period are processed to form multivariate time series. These time series are then used as input to different machine learning models for time series classification. The best method involves a transform called Random Convolutional Kernel Transform that extracts features from the time series. These features are then used as input to a logistic regression model that generates probabilities of the different class labels. This method achieves a ROC AUC-score of 0.856 when classifying customers as being involved in financial crime or not. The results indicate that the time series models detect patterns in transaction data that connect customers to financial crime which previously investigated methods have not been able to find.

Allt fler banker tillämpar artificiell intelligens (AI) i syfte att bekämpa finansiell brottslighet. Med den ökade användningen av AI uppkommer etiska utmaningar som banker behöver hantera för att säkerställa en god etik vid nyttjande av AI vid finansiell brottsbekämpning. Syftet med studien var att undersöka vilka ställningstaganden som ligger till grund för hur banker som använder AI hanterar etiska utmaningar inom finansiell brottslighet. Studien bygger på en kvalitativ ansats med semistrukturerade intervjuer för insamling av empiri samt en litteraturstudie för att besvara frågeställningen. En tematisk analys har gjorts för hur banker hanterar etiska utmaningar vid nyttjandet av AI för att bekämpa finansiell brottslighet, vilket ledde till följande slutsatser: banker hanterar etik både på individuell och organisatorisk nivå genom att undvika partiskhet, följa lagkrav, vara transparenta gentemot kunder att de övervakas samt följa upp beslut fattade av AI. Studiens resultat diskuteras utifrån etiska förhållningssätt såsom utilitarism, pliktetik och dygdetik. / More and more banks are applying artificial intelligence (AI) to fight financial crime. With the increased use of AI, ethical challenges arise that banks need to handle in order to ensure good ethics when using AI when fighting financial crime. The purpose of the study was to investigate which stances are the basis for how banks that use AI handle ethical challenges in financial crime. The study is based on a qualitative approach with semi-structured interviews to gather empirical evidence and a literature study to answer the research question. A thematic analysis has been made of how banks deal with ethical challenges when using AI to fight financial crime, which led to the following conclusions: banks deal with ethics both at an individual and organizational level by avoiding bias, complying with legal requirements but using the exceptions that exist for combating money laundering, being transparent to customers that they are being monitored, following up on decisions made by AI. The study's results are discussed based on different ethical approaches such as utilitarianism, duty ethics and virtue ethics.