Paper: arXiv 2410.07220

Authors: Opeyemi Sheu Alamu, Md Kamrul Siam

Abstract

A comparative analysis of deep learning models and traditional statistical methods for stock price prediction uses data from the Nigerian stock exchange. Historical data, including daily prices and trading volumes, are employed to implement models such as Long Short Term Memory (LSTM) networks, Gated Recurrent Units (GRUs), Autoregressive Integrated Moving Average (ARIMA), and Autoregressive Moving Average (ARMA). These models are assessed over three-time horizons: short-term (1 year), medium-term (2.5 years), and long-term (5 years), with performance measured by Mean Squared Error (MSE) and Mean Absolute Error (MAE). The stability of the time series is tested using the Augmented Dickey-Fuller (ADF) test. Results reveal that deep learning models, particularly LSTM, outperform traditional methods by capturing complex, nonlinear patterns in the data, resulting in more accurate predictions. However, these models require greater computational resources and offer less interpretability than traditional approaches. The findings highlight the potential of deep learning for improving financial forecasting and investment strategies. Future research could incorporate external factors such as social media sentiment and economic indicators, refine model architectures, and explore real-time applications to enhance prediction accuracy and scalability.

Complexity vs Empirical Score

  • Math Complexity: 5.0/10
  • Empirical Rigor: 6.0/10
  • Quadrant: Holy Grail — high math complexity, high empirical rigor

Why this score: The paper uses standard time-series statistical models (ARIMA/ARMA) and deep learning architectures (LSTM/GRU) with defined evaluation metrics (MSE, MAE, ADF test), demonstrating solid empirical setup with real-world financial data, though it lacks the heavy theoretical derivations typical of ‘Holy Grail’ papers.

Research Flowchart

  flowchart TD
  A["Research Goal"] -->|"Analyze"| B["Data Collection"]
  B --> C["Data Preprocessing"]
  C --> D{"Model Implementation"}
  D -->|"Traditional"| E["ARIMA / ARMA"]
  D -->|"Deep Learning"| F["LSTM / GRU"]
  E & F --> G["Evaluation Metrics<br>MSE, MAE"]
  G --> H["Key Findings"]
  
  subgraph B ["Data Inputs"]
      B1["NSE Historical Data"]
      B2["Daily Prices & Volumes"]
      B3["ADF Stationarity Test"]
  end
  
  subgraph D ["Time Horizons"]
      D1["Short-term: 1 Year"]
      D2["Medium-term: 2.5 Years"]
      D3["Long-term: 5 Years"]
  end
  
  subgraph H ["Outcomes"]
      H1["LSTM Outperforms Traditional Models"]
      H2["Captures Complex Nonlinear Patterns"]
      H3["Limited Interpretability & Higher Computation"]
  end

Evidence Card

What the authors claim, on what data, and who has checked it. Read from the paper's own text by a language model: every quote is verbatim, nothing was re-run. How to read this card

Proposes

The paper conducts a comparative analysis of deep learning models versus traditional statistical methods for stock price prediction on the Nigerian stock exchange.

Source sentence
A comparative analysis of deep learning models and traditional statistical methods for stock price prediction uses data from the Nigerian stock exchange.

Assumes 2

  • The stock price time series is stationary. statistical
    Source sentence
    we reject the null hypothesis and conclude that the time series data for stock prices in the Nigerian stock market is stationary.
  • The daily price and volume data obtained via the Yfinance API are accurate and up‑to‑date. data
    Source sentence
    The dataset used in this study was obtained from reliable financial databases and covers daily stock prices for the specified period

Data

  • Yfinance daily stock price dataset · Yfinance API market-prices public
    January 2019 to February 2019 (sample sh · Nigerian stock exchange stocks
    Source sentence
    The dataset used in this study was obtained from reliable financial databases and covers daily stock prices for the specified period

Recognised sources: Yahoo Finance

Costs

Not applicable The paper reports no trading or execution result.

Finds 2

  • In short‑term prediction, LSTM achieved an R‑squared of 0.9885 and GRU 0.9796, far outperforming ARIMA (‑1.7288) and ARMA (‑1.4705). performance
    Source sentence
    The LSTM model showed impressive performance, with an R-squared value of 0.9885
  • Overall, deep learning models generally outperformed traditional ARIMA/ARMA models across short, medium, and long‑term horizons. predictive-accuracy
    Source sentence
    The analysis and results demonstrated that deep learning models generally out‑performed traditional models in predicting stock prices across short-, medium-, and long-term horizons.

Checked by others

No other paper in the archive has been found to support or contradict these findings (compared with 21 related papers). Coverage is partial, so this is neither replication nor refutation.

Code

No repository by the authors found in the paper.

Extracted 2026-11-14 · same card as JSON · A language model chose these items: check the source sentence before relying on one.