Neuroevolution Neural Architecture Search for Evolving RNNs in Stock Return Prediction and Portfolio Trading

ArXiv ID: 2410.17212 “View on arXiv”

Authors: Unknown

Abstract

Stock return forecasting is a major component of numerous finance applications. Predicted stock returns can be incorporated into portfolio trading algorithms to make informed buy or sell decisions which can optimize returns. In such portfolio trading applications, the predictive performance of a time series forecasting model is crucial. In this work, we propose the use of the Evolutionary eXploration of Augmenting Memory Models (EXAMM) algorithm to progressively evolve recurrent neural networks (RNNs) for stock return predictions. RNNs are evolved independently for each stocks and portfolio trading decisions are made based on the predicted stock returns. The portfolio used for testing consists of the 30 companies in the Dow-Jones Index (DJI) with each stock have the same weight. Results show that using these evolved RNNs and a simple daily long-short strategy can generate higher returns than both the DJI index and the S&P 500 Index for both 2022 (bear market) and 2023 (bull market).

Keywords: Recurrent Neural Networks (RNN), Evolutionary Algorithms, Stock Return Forecasting, Long-Short Strategy, Time Series Prediction, Equities

Complexity vs Empirical Score

• Math Complexity: 3.0/10
• Empirical Rigor: 5.5/10
• Quadrant: Street Traders
• Why: The paper uses standard machine learning models (RNNs) and evolutionary algorithms without heavy mathematical derivations, but is heavily implementation-focused with a specific backtested portfolio strategy and performance metrics against market indices.

  flowchart TD
    A["Research Goal<br>Optimize Stock Returns via<br>Evolved RNN Forecasting"] --> B["Data Preparation<br>DJI 30 Stocks Historical Data"]
    B --> C{"Methodology<br>EXAMM Algorithm"}
    C --> D["Evolutionary Process<br>Neuroevolution of RNN Architectures"]
    D --> E["Predictive Modeling<br>Individual Stock Return Forecasts"]
    E --> F["Portfolio Strategy<br>Daily Long-Short Execution<br>Equal Weight DJI Portfolio"]
    F --> G["Key Findings<br>Outperformed DJI & S&P 500<br>Bear (2022) & Bull (2023) Markets"]