Paper: arXiv 2412.05297

Authors: Ali Abrishami, Jafar Habibi, AmirAli Jarrahi, Dariush Amiri, MohammadAmin Fazli

Abstract

Financial markets are integral to a country’s economic success, yet their complex nature raises challenging issues for predicting their behaviors. There is a growing demand for an integrated system that explores the vast and diverse data in financial reports with powerful machine-learning models to analyze financial markets and suggest appropriate investment strategies. This research provides an end-to-end decision support system (DSS) that pervasively covers the stages of gathering, cleaning, and modeling the stock’s financial and fundamental data alongside the country’s macroeconomic conditions. Analyzing and modeling the fundamental data of securities is a noteworthy method that, despite its greater power, has been used by fewer researchers due to its more complex and challenging issues. By precisely analyzing securities’ fundamental data, the proposed system assists investors in predicting stock future prices and allocating assets in major financial markets: stock, bond, and commodity. The most notable contributions and innovations of this research are: (1) Developing a robust predictive model for mid- to long-term stock returns, tailored for investors rather than traders, (2) The proposed DSS considers a diverse set of features relating to the economic conditions of the company, including fundamental data, stock trading characteristics, and macro-economic attributes to enhance predictive accuracy, (3) Evaluating the DSS performance on the Tehran Stock Exchange that has specific characteristics of small to medium-sized economies with high inflation rates and showing the superiority to novel researches, and (4) Empowering the DSS to generate different asset allocation strategies in various economic situations by simulating expert investor decision-making.

Complexity vs Empirical Score

  • Math Complexity: 2.0/10
  • Empirical Rigor: 6.0/10 (capped from 7.0: transaction costs not modelled; see penalty flags)
  • Quadrant: Street Traders — empirical and applied, lower math complexity (effective empirical rigor capped from 7.0)

Why this score: The paper focuses on applied machine learning with fundamental data and a full decision support system, relying on practical implementation rather than advanced mathematics, and includes evaluation on a real dataset with comparisons to baselines.

Research Flowchart

  flowchart TD
  A["Research Goal<br>Develop an integrated DSS for stock selection<br>and asset allocation using fundamental data"] --> B
  
  subgraph B ["Key Methodology & Data Inputs"]
      direction LR
      B1["Financial Data<br>Balance Sheet, Income Statement"] --> B3["Data Processing<br>Cleaning, Feature Engineering"]
      B2["Macroeconomic Data<br>Inflation, GDP, Interest Rates"] --> B3
  end

  B3 --> C["Computational Process<br>Machine Learning Models for Prediction"]
  C --> D{"Stock Selection<br>Predict Mid-Long Term Returns"}
  D --> E
  
  subgraph E ["Key Findings & Outcomes"]
      direction LR
      E1["High Predictive Accuracy<br>Superior to Novel Research"]
      E2["Adaptive Asset Allocation<br>Strategies for: Stocks, Bonds, Commodities"]
      E3["Robust DSS for<br>Mid-Long Term Investors"]
  end

  E1 & E2 & E3 --> F["Final Outcome<br>End-to-End Decision Support System<br>Evaluates Tehran Stock Exchange Market"]

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 robust predictive model for mid- to long-term stock returns and an end‑to‑end decision support system that also generates asset allocation strategies.

Source sentence
Developing a robust predictive model for mid- to long-term stock returns, tailored for investors rather than traders

Assumes 5

  • Adjusted stock prices are used, normalized for capital increase and dividends. data
    Source sentence
    For stock return prediction, we used adjusted stock prices (that were normalized with regard to capital increase and DPS).
  • The model outputs a probability between 0 and 1 representing confidence in future stock return. model
    Source sentence
    0 and 1 that higher probability shows the model’s confidence about future stock return.
  • Fundamental and macro‑economic features are sufficient to predict stock returns. model
    Source sentence
    The better modeling of market and macroeconomic features that influence stock price and adopting more powerful and more diverse features that explore the market behavior.
  • Classification of stock returns (rather than regression) is appropriate for forecasting direction and strategy development. model
    Source sentence
    Modeling the problem as a classification task and forecasting the price in comparison to fixed-income ETF return helps to better investigate stock direction and strategy development.
Show 1 more
  • The Tehran Stock Exchange data from 2015‑2024 is representative of high‑inflation economies. market
    Source sentence
    The dataset consists of 413 stocks in the Tehran Stock Exchange (TSE) that publish financial reports regularly... The

Data

  • Tehran Stock Exchange (TSE) fundamentals dataset fundamentals unknown
    2015-2024 · 413 TSE stocks
    Source sentence
    The dataset consists of 413 stocks in the Tehran Stock Exchange (TSE) that publish financial reports regularly. ... The

Costs

Not modeled A trading or execution result is reported without costs.

Finds 2

  • The proposed method achieves higher prediction accuracy than baselines across multiple horizons, e.g., 79% for 3‑month returns versus 63% for the best baseline. predictive-accuracy
    Source sentence
    Proposed (%) 64 65 79 79 73 74 67 61 ... Baseline-1 (%) 68 58 50 58 59 58 56 58 ... Baseline-2 (%) 70 61 63 59 58 59 63 60
  • Portfolio experiments show the proposed method yields superior periodic and cumulative returns compared to baseline strategies. performance
    Source sentence
    The results show the superiority of the proposed method to baselines.

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.

Cited References (50)

  1. Understanding inflation-indexed bond markets (2009)
  2. The intelligent investor (2005)
  3. Stock markets, banks, and economic growth (1998)
  4. Bond markets and economic growth (2003)
  5. Institutional and individual investors: Saving for old age (2018) — link
  6. Financial applications of machine learning: A literature review (2023) — link
  7. Stock market prediction using artificial intelligence: A systematic review of systematic reviews (2024) — link
  8. Evaluating multiple classifiers for stock price direction prediction (2015) — link
and 42 more
  1. An empirical evaluation of accounting income numbers (2013)
  2. Efficient capital markets (1970)
  3. Security analysis (1934)
  4. Machine learning techniques and data for stock market forecasting: A literature review (2022)
  5. Combining multiple feature selection methods for stock prediction: Union, intersection, and multi-intersection approaches (2010)
  6. Stock Selection Using Machine Learning Based on Financial Ratios (2023)
  7. Combining LSTM and CNN methods and fundamental analysis for stock price trend prediction (2023)
  8. Predictability of stock returns using neural networks: Elusive in the long term (2023) — link
  9. Deep architectures for long-term stock price prediction with a heuristic-based strategy for trading simulations (2019)
  10. Uncovering the relationship between incidental emotion toward a disaster and stock market fluctuations: Evidence from the US market (2024) — link
  11. A novel Deep Reinforcement Learning based automated stock trading system using cascaded LSTM networks — → 2212.02721
  12. Investment strategies applied to the Brazilian stock market: A methodology based on Sentiment Analysis with deep learning (2021) — link
  13. Deep learning models for price forecasting of financial time series: A review of recent advancements: 2020–2022 — → 2305.04811
  14. Financial time series forecasting with deep learning: A systematic literature review: 2005–2019 (2020)
  15. Forecasting stock market indices using padding-based fourier transform denoising and time series deep learning models (2021)
  16. Predicting stock market index using LSTM (2022) — link
  17. A hybrid model integrating deep learning with investor sentiment analysis for stock price prediction (2021) — link
  18. Applying machine learning algorithms to predict the stock price trend in the stock market–The case of Vietnam (2024)
  19. Comparative analysis between the fundamental and technical analysis of stocks (2016)
  20. A random walk down Wall Street: including a life-cycle guide to personal investing (1999)
  21. The elements of Investing (2009)
  22. A systematic review of fundamental and technical analysis of stock market predictions (2020)
  23. Stock Market Forecasting Using Deep Learning and Technical Analysis: A Systematic Review (2020) — link
  24. Deep learning in the stock market—a systematic survey of practice, backtesting, and applications (2023)
  25. An improved DenseNet model for prediction of stock market using stock technical indicators (2023) — link
  26. The importance of financial ratios in predicting stock price trends: A case study in emerging markets (2016)
  27. Deep Learning for Forecasting Stock Returns in the Cross-Section (2018)
  28. Stock return predictability with financial ratios (2011)
  29. MISMIS – A comprehensive decision support system for stock market investment (2010) — link
  30. A survey of decision support system applications (1995–2001) (2006)
  31. A decision support system for the stock market through integration of fuzzy neural networks and fuzzy Delphi (1998)
  32. A comprehensive decision support system for stock investment decisions (2022) — link
  33. Distilling wisdom of crowds in online communities: A novel prediction market constructed with comment posters (2024) — link
  34. A hybrid decision support system for adaptive trading strategies: Combining a rule-based expert system with a deep reinforcement learning strategy (2024) — link
  35. An adaptive stock index trading decision support system (2016) — link
  36. Decision support system for stock portfolio selection using artificial intelligence and machine learning. (2021)
  37. LSTM based decision support system for swing trading in stock market (2022) — link
  38. Recurrent neural network and a hybrid model for prediction of stock returns (2015) — link
  39. Asset allocation (2010)
  40. Asset Allocation: From Markowitz to Deep Reinforcement Learning (2022) — link
  41. Feature Selection for Stock Market Analysis (2013)
  42. Survey of feature selection and extraction techniques for stock market prediction (2023)

2 of 50 cited works are in the corpus; resolved via arXiv source bundles, Semantic Scholar and OpenAlex. Corpus-wide: 2596 linked papers.