Explore publications.

This study aims to enhance credit risk identification, improve loan borrower review efficiency, and increase default prediction accuracy rate using data mining and machine learning techniques. The study also employs deep learning to develop a consumer loan default prediction model that minimizes credit risks and ensures consistent development. The researchers collected data from a survey of 1000 participants, stratified into local and foreign banks, and selected the top 11 banks based on turnover and customer volume. To construct the machine learning model, Keras, a neural network library that runs on TensorFlow, was utilized. The model predicts loan applicant default likelihood. The study's practical implications demonstrate a noteworthy success rate of customer default prediction, which can significantly benefit banks. The model was evaluated on a test set of 250 records and achieved a test set accuracy of 95.2%, correctly predicting the default state of 238 out of 250 respondents.

The paper examines four main sources of financial risk exposure for four banks in the United Arab Emirates during the years 2003 to 2009. It begins by measuring stability levels for different types of financial risks using the coefficient of variation measure. The research then proceeds to investigate the nature of the relationship between financial risk and the actual reported financial performance of each company, namely the return on equity and return on assets. The findings show that all four sources of financial risk showed significant stability while both profitability indicators exhibited significant instability over the same period. Moreover, performance on the return on assets indicator was strongly and positively tied to a company’s return on equity indicator across the four banks but exhibited little or no interconnection with the four types of risks that banks are commonly exposed.