A Novel Fuzzy Associative Memory Architecture for Stock Market Prediction and Trading

Abstract

In this paper, a novel stock trading framework based on a neuro-fuzzy associative memory (FAM) architecture is proposed. The architecture incorporates the approximate analogical reasoning schema (AARS) to resolve the problem of discontinuous (staircase) response and inefficient memory utilization with uniform quantization in the associative memory structure. The resultant structure is conceptually clearer and more computationally efficient than the Compositional Rule Inference (CRI) and Truth Value Restriction (TVR) fuzzy inference schemes. The local generalization characteristic of the associative memory structure is preserved by the FAM-AARS architecture. The prediction and trading framework exploits the price percentage oscillator (PPO) for input preprocessing and trading decision making. Numerical experiments conducted on real-life stock data confirm the validity of the design and the performance of the proposed architecture.