Paper: arXiv 2311.06278

Authors: Md Sabbirul Haque, Md Shahedul Amin, Jonayet Miah, Duc Minh Cao, Ashiqul Haque Ahmed

Abstract

Prediction of stock prices plays a significant role in aiding the decision-making of investors. Considering its importance, a growing literature has emerged trying to forecast stock prices with improved accuracy. In this study, we introduce an innovative approach for forecasting stock prices with greater accuracy. We incorporate external economic environment-related information along with stock prices. In our novel approach, we improve the performance of stock price prediction by taking into account variations due to future expected macroeconomic policy changes as investors adjust their current behavior ahead of time based on expected future macroeconomic policy changes. Furthermore, we incorporate macroeconomic variables along with historical stock prices to make predictions. Results from this strongly support the inclusion of future economic policy changes along with current macroeconomic information. We confirm the supremacy of our method over the conventional approach using several tree-based machine-learning algorithms. Results are strongly conclusive across various machine learning models. Our preferred model outperforms the conventional approach with an RMSE value of 1.61 compared to an RMSE value of 1.75 from the conventional approach.

Complexity vs Empirical Score

  • Math Complexity: 2.0/10
  • Empirical Rigor: 6.5/10
  • Quadrant: Street Traders — empirical and applied, lower math complexity

Why this score: The paper’s mathematics is relatively elementary, focusing on standard regression and machine learning metrics like RMSE without advanced derivations. However, it demonstrates strong empirical rigor through its use of multiple real-world datasets, feature engineering, cross-model validation, and clear performance metrics.

Research Flowchart

  flowchart TD
  A["Research Goal: Enhance Stock Price Prediction"] --> B["Methodology: Feature Engineering & ML"]
  B --> C["Data Inputs: Historical Stock Prices, Current &<br>Anticipated Future Macro Policy Changes"]
  C --> D["Computational Process: Tree-Based ML Models"]
  D --> E["Model Training &<br>Performance Evaluation"]
  E --> F{"Comparison:<br>Proposed vs Conventional"}
  F -->|"Outcomes"| G["Proposed Model Outperforms"]
  G --> H["Key Findings: Lower RMSE (1.61 vs 1.75)<br>Future Policy Data Significantly Improves Accuracy"]

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 proposes a novel stock price forecasting approach that augments historical prices with macroeconomic indicators and anticipated future policy changes, using tree‑based machine‑learning models.

Source sentence
In this study, we introduce an innovative approach for forecasting stock prices with greater accuracy. We incorporate external economic environment-related information along with stock prices. In our novel approach, we improve the performance of stock price prediction by taking into account variations due to future exp

Assumes 4

  • Future interest rates can be used as a proxy for expected future interest rates. other
    Source sentence
    In our study, we incorporate future interest rates as a proxy for future expected interest rates along with other macroeconomic indicators
  • Selecting the ten S&P 500 tickers with the highest maximum partial autocorrelation provides a suitable sample for time‑series modeling. data
    Source sentence
    We choose the first ten ticker symbols in that ranked list. We select ticker symbols in this way to select those ticker symbols that have strong serial autocorrelation, which is essential for building a time-series model.
  • Macroeconomic variables (CPI, unemployment, current and future interest rates) have a statistically significant relationship with stock prices. statistical
    Source sentence
    Results from Table 2 provide empirical evidence that all proposed economic variables, along with expected macroeconomic policy variables, have a statistically significant relation with the stock price.
  • Tree‑based machine‑learning models can capture the effect of macro variables on stock price movements. model
    Source sentence
    We train three tree-based machine-learning models using two datasets: with and without our proposed variables.

Data

  • Historical daily stock price data for S&P 500 ticker symbols · Yahoo Finance market-prices public
    S&P 500 constituents
    Source sentence
    Historical daily stock price data for S&P500 ticker symbols have been collected from publicly available Yahoo Finance.
  • Interest rate data · FRED macro public
    Source sentence
    Interest rates are collected from Fred’s data repository.
  • Unemployment rate data · World Bank World Development Indicators macro public
    Source sentence
    ... have been collected from the World Bank’s World Development Indicators (WDI) database.
  • Consumer Price Index (CPI) data · World Bank World Development Indicators macro public
    Source sentence
    Consumer Price Index (CPI) data have been collected from the World Bank’s World Development Indicators (WDI) database.

Costs

Not applicable The paper reports no trading or execution result.

Finds 3

  • The best‑performing LightGBM model using the proposed macro features achieves an RMSE of 1.61, compared with 1.75 for the conventional model without those features. performance
    Source sentence
    Specifically, we report an RMSE value of 1.61 yielded by the best-performing model (LGBM) using our novel approach, whereas the conventional counterpart (LGBM without our proposed features) generates an RMSE value of 1.75.
  • All three tree‑based models (LightGBM, XGB, Decision Tree) show lower RMSE and MAE when trained with the proposed macro variables, except the Decision Tree RMSE which slightly increases. predictive-accuracy
    Source sentence
    three models trained on a dataset that includes our proposed variables display superior performance compared to that trained on a dataset without such variables in terms of both RMSE and MAE, with one exception.
  • Statistical tests confirm that each of the introduced macroeconomic and expected policy variables is significantly related to stock price movements. statistical
    Source sentence
    Results from Table 2 provide empirical evidence that all proposed economic variables, along with expected macroeconomic policy variables, have a statistically significant relation with the stock price.

Checked by others

No other paper in the archive has been found to support or contradict these findings (compared with 11 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.