Search

This study aims to develop a better Financial Statement Fraud (FSF) detection model by utilizing data from publicly available financial statements of firms in the MENA region. We develop an FSF model using a powerful ensemble technique, the XGBoost (eXtreme Gradient Boosting) algorithm, that helps to identify fraud in a set of sample companies drawn from the Middle East and North Africa (MENA) region. The issue of class imbalance in the dataset is addressed by applying the Synthetic Minority Oversampling Technique (SMOTE) algorithm. We use different Machine Learning techniques in Python to predict FSF, and our empirical findings show that the XGBoost algorithm outperformed the other algorithms in this study, namely, Logistic Regression (LR), Decision Tree (DT), Support Vector Machine (SVM), AdaBoost, and Random Forest (RF). We then optimize the XGBoost algorithm to obtain the best result, with a final accuracy of 96.05% in the detection of FSF. [ABSTRACT FROM AUTHOR]

Financial Distress Prediction has been a critical concern in the field of finance that sparked a slew of academic interests in the area. In our study, we examine the performance of various data mining models for predicting financial distress in companies in the Middle East and North Africa area, followed by model optimization. The main goal of the study is to find the most reliable deep neural network model for financial distress prediction, with optimized parameters. The study is divided into three phases. The output of various single machine learning classifiers and ensemble techniques for predicting financial distress is compared in the first phase. The best classifier found in the first step, the neural network, is then given different number of hidden layers. Furthermore, to achieve better prediction performance than the second stage, the Multi-Layer Perceptron model is optimised by tuning the hyperparameters such as network depth and network width. The prediction performance of the models is evaluated using real-time data sets containing samples of companies from the MENA region. The technique of re-sampling is used, for all the models, in order to get accurate and unbiased results. [ABSTRACT FROM AUTHOR]