Leveraging quantum-inspired chimp optimization and deep neural networks for enhanced profit forecasting in financial accounting systems

Deep learning and metaheuristic algorithms have recently increased in various sciences, including financial accounting information systems (FAISs). However, the existence of large datasets has dramatically increased the complexity of these hybrid networks, so to address this shortcoming, this paper aims to develop a quantum-behaved chimp optimization algorithm (QCHOA) and deep neural network (DNN) for the prediction of the profit based on FAISs. Considering that there is no suitable dataset for the challenge, a novel dataset is developed utilizing the 15 features from the Chinese market dataset to compare more. This work designs QCHOA and five DNN-based predictors to forecast profit. These algorithms include the universal learning CHOA (ULCHOA), the niching CHOA (NCHOA) as the two best-modified versions of CHOA, the quantum-behaved whale optimization algorithm (QWOA), and the quantum-behaved grey wolf optimizer (QGWO) as the two best quantum-behaved optimizers as well as classic CHOA. The most effective deep learning-based predictors for forecasting the profit, ranked from highest to lowest, are DNN-QCHOA, DNN-NCHOA, DNN-QWOA, DNN-QGWO, DNN-ULCHOA, DNN-CHOA, and classic DNN, with corresponding ranking scores of 42, 36, 30, 24, 18, 12, and 6. As a final suggestion for profit prediction, the DNN-CHOA is shown to be the most accurate model.