The problem of imbalanced datasets is a significant concern when creating reliable credit card fraud (CCF) detection systems. In this work, we study and evaluate recent advances in machine learning (ML) algorithms and deep reinforcement learning (DRL) used for CCF detection systems, including fraud and non-fraud labels. Based on two resampling approaches, SMOTE and ADASYN are used to resample the imbalanced CCF dataset. ML algorithms are, then, applied to this balanced dataset to establish CCF detection systems. Next, DRL is employed to create detection systems based on the imbalanced CCF dataset. The diverse classification metrics are indicated to thoroughly evaluate the performance of these ML and DRL models. Through empirical experiments, we identify the reliable degree of ML models based on two resampling approaches and DRL models for CCF detection. When SMOTE and ADASYN are used to resampling original CCF datasets before training/test split, the ML models show very high outcomes of above 99% accuracy. However, when these techniques are employed to resample for only the training CCF datasets, these ML models show lower results, particularly in terms of logistic regression with 1.81% precision and 3.55% F1 score for using ADASYN. Our work reveals the DRL model is ineffective and achieves low performance, with only 34.8% accuracy.

Large amounts of data is generated every second over the Internet, and thus making a proper decision is crucial. Even if we have collected a lot of data, extracting the beneficial knowledge inside the data is a challenging task. The reasons for this difficulty include: 1) data are not normally clean, especially they are obtained from different sources, and 2) data can be redundant or duplicated. Therefore, it is necessary to have a data cleaning process, which is used to detect any anomalies within the data. Additionally, the process can identify any inconsistencies or duplication at an early stage. In this study, we introduce Open ^K , an efficient elastic data cleansing system based on clustering methods. Data are clustered based on metrics of similarity generated by different techniques such as: nearest neighbour (e.g. Levenshtein, Damerau-Levenshtein, and Hamming distances), similarity measurement (e.g., Jaro and Jaro-Winkler Distance Similarity), and key collision (e.g., Fingerprints and N-gram fingerprints). Our prototype can run on Windows operating system with an installed AzureCosmosDB version to support a friendly web-based interface and a wide array of input formats. Experimental results show that our tool outperforms existing software in terms of efficiency and practical perspectives.