Abstract
In the realm of foreign exchange (Forex) market predictions, Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) have been commonly employed. However, these models often exhibit instability due to vulnerability to data perturbations attributed to their monolithic architecture. Hence, this study proposes a novel neuroscience-informed modular network that harnesses closing prices and sentiments from Yahoo Finance and Twitter APIs. Compared to monolithic methods, the objective is to advance the effectiveness of predicting price fluctuations in Euro to British Pound Sterling (EUR/GBP). The proposed model offers a unique methodology based on a reinvigorated modular CNN, replacing pooling layers with orthogonal kernel initialisation RNNs coupled with Monte Carlo Dropout (MCoRNNMCD). It integrates two pivotal modules: a convolutional simple RNN and a convolutional Gated Recurrent Unit (GRU). These modules incorporate orthogonal kernel initialisation and Monte Carlo Dropout techniques to mitigate overfitting, assessing each module’s uncertainty. The synthesis of these parallel feature extraction modules culminates in a three-layer Artificial Neural Network (ANN) decision-making module. Established on objective metrics like the Mean Square Error (MSE), rigorous evaluation underscores the proposed MCoRNNMCD–ANN’s exceptional performance. MCoRNNMCD–ANN surpasses single CNNs, LSTMs, GRUs, and the state-of-the-art hybrid BiCuDNNLSTM, CLSTM, CNN–LSTM, and LSTM–GRU in predicting hourly EUR/GBP closing price fluctuations.
Abstract
Financial decision-making, a cornerstone of individual prosperity and global economic stability, is hard to comprehend because it is a complex cognitive process concerned with emotional state and behavioural bias. This paper aims to decode the neural mechanisms behind financial behaviour to advance theoretical and empirical progress in neurofinance. Thus, to better capture financial behaviour, this article proposes an innovative framework that bridges neurofinance, neuroscience, and bio-inspired computational models, like the MCoRNNMCD-ANN. Key research areas include the role of neural processes driving decisions, the effect of cognitive preferences on judgment, and the potential of bio-inspired AI models to enhance understanding. The societal implications of this research seek to encourage equitable, stable and informed financial systems while addressing challenges at the intersection of neurofinance and neuroscience-informed AI.