Neural Network Models for Stock Selection Based on Fundamental Analysis

TL;DR

This paper compares neural network models, specifically FNN and ANFIS, for stock prediction using financial ratios, demonstrating that both can outperform benchmarks with FNN showing superior results.

Contribution

It provides a comparative analysis of FNN and ANFIS architectures for stock selection based on fundamental analysis, highlighting FNN's superior performance.

Findings

Both models can distinguish winners from losers.

Selected portfolios outperform the benchmark index.

FNN shows better performance than ANFIS.

Abstract

Application of neural network architectures for financial prediction has been actively studied in recent years. This paper presents a comparative study that investigates and compares feed-forward neural network (FNN) and adaptive neural fuzzy inference system (ANFIS) on stock prediction using fundamental financial ratios. The study is designed to evaluate the performance of each architecture based on the relative return of the selected portfolios with respect to the benchmark stock index. The results show that both architectures possess the ability to separate winners and losers from a sample universe of stocks, and the selected portfolios outperform the benchmark. Our study argues that FNN shows superior performance over ANFIS.