Over the years, financial engineering ranging from the study of financial signals to the modelling of financial prediction is one of the most exciting topics for both academia and financial community. With the flourishing of AI technology in the past 20 years, various hybrid intelligent financial prediction systems with the integration of neural networks, chaos theory, fuzzy logic and genetic algorithms have been proposed. Interval Type-2 Fuzzy Logic System (IT2FLS) with its remarkable capability for the modelling of highly uncertain events and attributes, provides a perfect tool to interpret various financial phenomena and patterns. In this paper, the author proposes a Chaotic Type-2 Transient-Fuzzy Deep Neuro-oscillatory Network with Retrograde Signaling (aka CT2TFDNN) for worldwide financial prediction. With the extension of author's original work on Lee-oscillator – a chaotic discrete-time neural oscillator with profound transient-chaotic property, CT2TFDNN provides: 1) effective modelling of Interval Type-2 Fuzzy Logic with Chaotic Transient-Fuzzy Membership Function (CT2TFMF); 2) effective time-series network training and prediction using Chaotic Deep Neuro-oscillatory Network with Retrograde Signaling (CDNONRS). CT2TFDNN not only provides a fast chaotic fuzzy-neuro deep learning and forecast solution, more prominently it successfully resolves the massive data over-training and deadlock problems which are usually imposed by traditional recurrent neural networks using classical sigmoid-based activation functions. From the implementation perspective, CT2TFDNN is integrated with 2048-trading day time-series financial data and Top-10 major financial signals as Fuzzy Financial Signals (FFS) for the real-time prediction of 129 worldwide financial products which consists of: 9 major cryptocurrencies, 84 worldwide forex, 19 major commodities and 17 worldwide financial indices.

Financial prediction persists a strenuous task in Fintech research. This paper introduces a multifractal asymmetric detrended cross-correlation analysis (MF-ADCCA)-based deep learning forecasting model to predict a succeeding day log return via excitatory and inhibitory neuronal synapse unit (EINS) using asymmetric Hurst exponent as input features, with return and volatility increment of Shanghai Stock Exchanges Composite Index (SSECI) from 2014 to 2020 as proxies for analysis. Experimental results revealed that multifractal elements by MF-ADCCA method as input features are applicable to time series forecasting in deep learning than multifractal detrended fluctuation analysis (MF-DFA) method. Further, the proposed biologically inspired EINS model achieved satisfactory performances in effectiveness and reliability in time series prediction compared with prevalent recurrent neural networks (RNNs) such as LSTM and GRU. The contributions of this paper are to (1) introduce a moving-window MF-ADCCA method to obtain asymmetric Hurst exponent sequences used directly as an input feature for deep learning prediction and (2) evaluate performances of various asymmetric multifractal approaches for deep learning time series forecasting.

Long Short-Term Memory (LSTM) networks are unique to exercise data in its memory cell with long-term memory as Natural Language Processing (NLP) tasks have inklings of intensive time and computational power due to their complex structures like magnitude language model Transformer required to pre-train and learn billions of data performing different NLP tasks. In this paper, a dynamic chaotic model is proposed for the objective of transforming neurons states in network with neural dynamic characteristics by restructuring LSTM as Chaotic Neural Oscillatory-Long-Short Term Memory (CNO-LSTM), where neurons in LSTM memory cells are weighed in substitutes by oscillatory neurons to speed up computational training of language model and improve text classification accuracy for real-world applications. From the implementation perspective, five popular datasets of general text classification including binary, multi classification and multi-label classification are used to compare with mainstream baseline models on NLP tasks. Results showed that the performance of CNO-LSTM, a simplified model structure and oscillatory neurons state in exercising different types of text classification tasks are above baseline models in terms of evaluation index such as Accuracy, Precision, Recall and F1. The main contributions are time reduction and improved accuracy. It achieved approximately 46.76% of the highest reduction training time and 2.55% accuracy compared with vanilla LSTM model. Further, it achieved approximately 35.86% in time reduction compared with attention model without oscillatory indicating that the model restructure has reduced GPU dependency to improve training accuracy.