Enhancing Profitability and Investor Confidence through Interpretable AI Models for Investment Decisions

TL;DR

The paper tackles the need for interpretable investment forecasting in volatile markets by proposing a SHAP-based explainable framework that integrates technical indicators (EMA, MACD, RSI) into a weighted voting ensemble to produce a daily and short-term trading signal on the Pakistan Stock Exchange. The approach computes a target feature $Z_t$ via a weighted vote function $wv(S,W)$ and leverages SHAP explanations (Kernel and Tree Explainer) to reveal feature contributions, comparing against RF and XGBoost baselines. Results show accuracies of approximately 63.36% for daily trading and 71.88% for short-term trading, with SHAP indicating EMA55, EMA100, and RSI as key drivers, and the method outperforming baselines. A four-year PSX case study demonstrates potential portfolio gains under both conservative and aggressive automation strategies, underscoring the practical value of interpretable AI in investment decision-making and suggesting directions toward more comprehensive data sources via NLFF and rule-based explanations.

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.

Figures (11)

• Figure 1:
• Figure 2:
• Figure 3:
• Figure 4:
• Figure 5: