Regresar

Data mining techniques to predict the financial performance of private banks in Ecuador

Abstract:

The purpose of this study is to apply a set of data mining techniques to anticipate the financial performance of private banks in Ecuador. Based on the monthly financial reports of these banks during the period from 2017 to 2023. Experimental results indicated that the optimal technique for predicting the financial performance of banks is the use of artificial neural networks (ANN), which provides the best predictive accuracy and offers an optimal understanding of financial performance. Additionally, the k-nearest neighbors method (KNN) produces values close to the optimal accuracy of neural networks, making it another robust technique to predict return on assets (ROA) as an indicator of the financial performance of the banking sector. The findings provide management with an advanced tool to assess the financial performance of banks based on investments in intellectual capital and its components.