Paper: arXiv 2312.16223

Authors: Sahar Arshad, Seemab Latif, Ahmad Salman, Rabia Latif

Abstract

Financial forecasting plays an important role in making informed decisions for financial stakeholders, specifically in the stock exchange market. In a traditional setting, investors commonly rely on the equity research department for valuable reports on market insights and investment recommendations. The equity research department, however, faces challenges in effectuating decision-making do to the demanding cognitive effort required for analyzing the inherently volatile nature of market dynamics. Furthermore, financial forecasting systems employed by analysts pose potential risks in terms of interpretability and gaining the trust of all stakeholders. This paper presents an interpretable decision-making model leveraging the SHAP-based explainability technique to forecast investment recommendations. The proposed solution not only provides valuable insights into the factors that influence forecasted recommendations but also caters the investors of varying types, including those interested in daily and short-term investment opportunities. To ascertain the efficacy of the proposed model, a case study is devised that demonstrates a notable enhancement in investor’s portfolio value, employing our trading strategies. The results highlight the significance of incorporating interpretability in forecasting models to boost stakeholders’ confidence and foster transparency in the stock exchange domain.

Complexity vs Empirical Score

  • Math Complexity: 3.5/10
  • Empirical Rigor: 6.0/10
  • Quadrant: Street Traders — empirical and applied, lower math complexity

Why this score: The paper uses standard ML metrics and SHAP for explainability, but lacks deep mathematical derivations or advanced statistical theory. Empirically, it includes a case study with portfolio value enhancement on a specific exchange, suggesting data-driven implementation, though detailed backtest specifics or code are not provided in the excerpt.

Research Flowchart

  flowchart TD
  A["Research Goal:<br>Enhance Profitability & Confidence<br>through Interpretable AI for Investment"] --> B["Data/Inputs:<br>Equity Market Data &<br>Historical Investment Patterns"]
  B --> C["Methodology:<br>SHAP-based<br>Explainability Technique"]
  C --> D["Computation:<br>Train Interpretable<br>Decision Model &<br>Generate Feature Importance"]
  D --> E["Implementation:<br>Apply Model to<br>Trading Strategies"]
  E --> F{"Evaluation"}
  F -->|"Case Study"| G["Key Findings/Outcomes:<br>1. Enhanced Portfolio Value<br>2. Increased Stakeholder Confidence<br>3. Transparent Forecasting"]
  F -->|"Feedback"| C

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 an interpretable decision‑making model that uses SHAP explainability to forecast investment recommendations.

Source sentence
This paper presents an interpretable decision-making model leveraging the SHAP-based explainability technique to forecast investment recommendations.

Assumes 1

  • Missing values are forward‑filled, assuming stock prices are stable from day to day. data
    Source sentence
    missing values were handled using a forward fill method, whereby the last observed value was replaced by the missing values since this is a reasonable assumption based on the stability of stock prices from day to day.

Data

  • PSX financial data market-prices unknown
    Source sentence
    We have compared our results with other state-of-the-art baseline approaches i.e., Random Forest and XGBoost to evaluate its performance and accuracy in forecasting the financial data of PSX

Recognised sources: StockTwits Twitter / X

Costs

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

Finds 3

  • The case study shows a notable enhancement in the investor’s portfolio value when using the proposed model. performance
    Source sentence
    a case study is devised that demonstrates a notable enhancement in investor’s portfolio value
  • The proposed statistical model yields better results in forecasting trading signals and provides enhanced interpretation. performance
    Source sentence
    the proposed statistical model provides a solid foundation for inference and yields better results in terms of forecasting trading signals and enhanced interpretation
  • The SHAP‑based model is compared against Random Forest and XGBoost baselines, showing competitive performance and interpretability. performance
    Source sentence
    We have compared our results with other state-of-the-art baseline approaches i.e., Random Forest and XGBoost to evaluate its performance and accuracy in forecasting the financial data of PSX, as well as its interpretability and explainability.

Checked by others

No other paper in the archive has been found to support or contradict these findings (compared with 20 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 (30)

  1. The psychology and neuroscience of financial decision making (2016)
  2. Fusion in stock market prediction: a decade survey on the necessity, recent developments, and potential future directions (2021)
  3. An interpretable decision-support systems for daily cryptocurrency trading (2022)
  4. Automated trading systems statistical and machine learning methods and hardware implementation: a survey (2019)
  5. Explainable AI in fintech risk management (2020)
  6. Explainable AI in credit risk management (2021) — link
  7. The benefits of using artificial intelligence in payment fraud detection: A case study (2018)
  8. Incorporating stock prices and news sentiments for stock market prediction: A case of Hong Kong (2020)
and 22 more
  1. Using artificial intelligence to create value in insurance (2018)
  2. Artificial Intelligence in Debt Collection (2019)
  3. International Financial Markets face to face with Artificial Intelligence and Digital Era. (2019)
  4. Explainable Artificial Intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI (2020)
  5. Explainable machine learning exploiting news and domain-specific lexicon for stock market forecasting (2021)
  6. Generating plausible counterfactual explanations for deep transformers in financial text classification (2020) — link
  7. Explainable stock prices prediction from financial news articles using sentiment analysis (2021)
  8. Sentiment-aware volatility forecasting (2019)
  9. Explainable text-driven neural network for stock prediction (2018)
  10. An AI-enabled stock prediction platform combining news and social sensing with financial statements (2021)
  11. When does attention matter? The effect of investor attention on stock market volatility around news releases (2022)
  12. The Dynamic Relationship between Investor Attention and Stock Market Volatility: International Evidence (2022)
  13. A neural stochastic volatility model (2018)
  14. Price linkage rumors in the stock market and investor risk contagion on bilayer-coupled networks (2019)
  15. Explainable AI for Financial Forecasting (2021) — link
  16. An explainable artificial intelligence tool for statistical arbitrage (2022)
  17. A unified approach to interpreting model predictions (2017)
  18. Large data sets and machine learning: Applications to statistical arbitrage (2019)
  19. Deep neural networks, gradient-boosted trees, random forests: Statistical arbitrage on the S&P 500 (2017)
  20. Machine learning for asset management: new developments and financial applications (2020)
  21. Natural language based financial forecasting: a survey (2018)
  22. A systematic review of fundamental and technical analysis of stock market predictions (2020)

0 of 30 cited works are in the corpus; resolved via arXiv source bundles, Semantic Scholar and OpenAlex. Corpus-wide: 2596 linked papers.