Recognizing fraudulent credit card transactions is one of the main issues facing banking institutions. Since each transaction that completes the authentication procedure must be authorized by financial institutions, a hacker might pose as the actual cardholder and execute a fraudulent transaction. In this paper, we investigated the capacity of ensemble learning methods to identify credit card frauds on two distinct data sets: the Sparkov synthetic data set and the real data set of consumers in the European Union. XGBoost models, random forests, and naive Bayes classifiers are applied and assessed on both data sets. Accuracy, precision, recall, and F1 score are used to measure performance. According to the results, most ensemble classifiers perform exceptionally well on the real-world dataset, but significantly poorly on the simulated dataset. This study showed that, unlike in simulated environments, credit card transaction management scripts are quickly learned in deterministic settings. It is discussed that a larger danger of card information leakage results from strict determinism and lack of randomness.
In classification, feature selection engineering helps in choosing the most relevant data attributes to learn from. It determines the set of features to be rejected, supposing their low contribution in discriminating the labels. The effectiveness of a classifier passes mainly through the set of selected features. In this paper, we identify the best features to learn from in the context of credit risk assessment in the financial industry. Financial institutions concur with the risk of approving the loan request of a customer who may default later, or rejecting the request of a customer who can abide by their debt without default. We propose a feature selection engineering approach to identify the main features to refer to in assessing the risk of a loan request. We use different feature selection methods including univariate feature selection (UFS), recursive feature elimination (RFE), feature importance using decision trees (FIDT), and the information value (IV). We implement two variants of the XGBoost classifier on the open data set provided by the Lending Club platform to evaluate and compare the performance of different feature selection methods. The research shows that the most relevant features are found by the four feature selection techniques.
The Home Care Scheduling Problem (HCSP) consists of designing a set of routes for medical service suppliers to visit a number of patients located at different places and asking for a set of medical tasks. The object of the HCSP is to define the required set of routes where the assigned workforce will travel in order to minimize the overall travelled distance. Therefore, the solution will define first the teams (crew) that will travel together for serving particular subset of patients. Then, the route of each team is defined. The problem shows a hierarchical nature where the solving algorithm should build first the service team that defines partially the set of potential customers to serve and then look for the routes to follow. In this paper, we studied and solved the HCSP after reviewing the literature on the HCSP. We modeled the HCSP as a multilevel (hierarchical) combinatorial optimization problem. Then, we focused on particular variant of the HCSP which is the Multiple Traveling Salesman Problem with Time windows (MTSPTW) where we implemented a Tabu Search based heuristic to solve a modified version of Solomons instances. The obtained results are reported, commented and validated.