BIOLOGICAL BRAIN‐INSPIRED GENETIC COMPLEMENTARY LEARNING FOR STOCK MARKET AND BANK FAILURE PREDICTION¹

Abstract

Genetic complementary learning (GCL) is a biological brain-inspired learning system based on human pattern recognition, and genes selection process. It is a confluence of the hippocampal complementary learning and the evolutionary genetic algorithm. With genetic algorithm providing the possibility of optimal solution, and complementary learning providing the efficient pattern recognition, GCL may offer superior performance. In contrast to other computational finance tools such as neural network and statistical methods, GCL provides greater interpretability and it does not rely on the assumption of the underlying data distribution. It is an evolving and autonomous system that avoids the time-consuming process of manual rule construction or modeling. This is highly favorable especially in financial world where data is ever changing, and requires frequent update. The feasibility of GCL as stock market predictor, and bank failure early warning system is investigated. The experimental results show that GCL is a competent computational finance tools for stock market prediction and bank failure early warning system.

Predicting direction of stock price index movement using artificial neural networks and support vector machines: The sample of the Istanbul Stock Exchange

“…Some researches tend to hybridize several artificial intelligence (AI) techniques to predict stock market returns (Baba & Kozaki, 1992;Chu, Chen, Cheng, & Huang, 2009;Hiemstra, 1995;Kim & Chun, 1998;Leigh, Purvis, & Ragusa, 2002;Oh & Kim, 2002;Pai & Lin, 2005;Saad, Prokhorov, & Wunsch, 1998;Takahashi, Tamada, & Nagasaka, 1998;Tan et al, 2007;Yudong & Lenan, 2009). Tsaih, Hsu, and Lai (1998) applied a hybrid AI approach to predict the direction of daily price changes in S&P 500 stock index futures.…”

“…In addition, stock market is affected by many macro economical factors such as political events, firms' policies, general economic conditions, investors' expectations, institutional investors' choices, movement of other stock market, and psychology of investors etc. (Tan, Quek, & See, 2007). ANN and SVM have been successfully used for modeling and predicting financial time series.…”

FCMAC-Yager: A Novel Yager-Inference-Scheme-Based Fuzzy CMAC

“…These research endeavors culminated with the developments of the human hippocampus-inspired learning memory systems such as GenSoFNN [66], pseudoadaptive complementary learning networks [68], and POPFNN [5], [49], [50], [54], as well as cerebellar-based computational models [64] for the modeling of complex, dynamic, and nonlinear problem domains. The application of these brain-inspired learning memory systems is actively pursued, and they have been successfully applied to automated driving [44], signature forgery detection [52], gear control for continuous-variable-transmission in automobile [4], fingerprint verification [51], medical decision-support [61], [70], and computational finance [7], [47], [62], [69]. APPENDIX A Please see Table V. …”

Big Data Analysis of StockTwits to Predict Sentiments in the Stock Market

“…The aim has been to create accurate models that have the ability to predict stock price behavioral movements in the stock market rather than predicting the investing decisions that derive from and cause the movement itself, such as the buying, selling and holding decisions. Investors' expectations and their psychological thinking from which the sentiments are derived are considered the main factors that affect stock price movements in capital markets [21]; it is therefore important to highlight the critical role played by trading decisions in the stock market. Trading decisions have a great effect on the profitability position of an investor in the capital market.…”