Earticle

With the fast development of artificial intelligence day by day, users are demanding explanations about the results of algorithms and want to know what parameters influence the results. In this paper, we propose a model for bankruptcy prediction with interpretability using the SHAP framework. SHAP (SHAPley Additive exPlanations) is framework that gives a visualized result that can be used for explanation and interpretation of machine learning models. As a result, we can describe which features are important for the result of our deep learning model. SHAP framework Force plot result gives us top features which are mainly reflecting overall model score. Even though Fully Connected Neural Networks are a “black box” model, Shapley values help us to alleviate the “black box” problem. FCNNs perform well with complex dataset with more than 60 financial ratios. Combined with SHAP framework, we create an effective model with understandable interpretation. Bankruptcy is a rare event, then we avoid imbalanced dataset problem with the help of SMOTE. SMOTE is one of the oversampling technique that resulting synthetic samples are generated for the minority class. It uses K-nearest neighbors algorithm for line connecting method in order to producing examples. We expect our model results assist financial analysts who are interested in forecasting bankruptcy prediction of companies in detail.

In this study we explore the integration of Large Language Models (LLMs), specifically GPT-4o-mini, with traditional stock market technical indicators—MACD, RSI, and Bollinger Bands—to enhance stock market prediction and decision-making frameworks. By combining quantitative analysis with qualitative insights generated by LLMs, this research demonstrates how artificial intelligence can improve the interpretability and predictive accuracy of technical trading strategies. Historical data for Tesla and Palantir, spanning six months, was analyzed with indicators calculated to identify market trends and anomalies. LLM integration provided contextual narratives that complemented technical signals, enhancing interpretability for investors. The performance evaluation revealed significant improvements in risk-adjusted returns, alpha generation, and prediction accuracy when LLM insights were incorporated into trading strategies. Key contributions include a novel methodology for structuring indicator outputs for LLM analysis, scalability across diverse stocks, and the potential for democratizing access to advanced financial analytics. Challenges such as computational complexity, data sensitivity, and the dynamic nature of financial markets are discussed, alongside opportunities for real-time adaptive models and expanded indicator integration. This research highlights the transformative potential of LLM-augmented technical analysis and offers a foundation for future innovations in AI-driven financial decision-making.