A Dynamic Approach to Stock Price Prediction: Comparing RNN and Mixture of Experts Models Across Different Volatility Profiles

TL;DR

This paper introduces a Mixture of Experts model that dynamically combines RNN and linear regression for stock price prediction, significantly improving accuracy across different market volatility profiles.

Contribution

The study proposes a novel MoE framework that adaptively integrates RNN and linear models based on stock volatility, outperforming individual models in predictive accuracy.

Findings

MoE outperforms individual RNN and linear models in accuracy.

RNN captures non-linear patterns in volatile stocks.

Linear model performs well on stable stocks.

Abstract

This study evaluates the effectiveness of a Mixture of Experts (MoE) model for stock price prediction by comparing it to a Recurrent Neural Network (RNN) and a linear regression model. The MoE framework combines an RNN for volatile stocks and a linear model for stable stocks, dynamically adjusting the weight of each model through a gating network. Results indicate that the MoE approach significantly improves predictive accuracy across different volatility profiles. The RNN effectively captures non-linear patterns for volatile companies but tends to overfit stable data, whereas the linear model performs well for predictable trends. The MoE model's adaptability allows it to outperform each individual model, reducing errors such as Mean Squared Error (MSE) and Mean Absolute Error (MAE). Future work should focus on enhancing the gating mechanism and validating the model with real-world datasets to optimize its practical applicability.