Search Results (20)

In the era of digital healthcare, electronic health records generate vast amounts of data, much of which is unstructured, and therefore, not in a usable format for conventional machine learning and artificial intelligence applications. This study investigates how to extract meaningful insights from unstructured radiology reports written in Finnish, a minority language, using machine learning techniques for text analysis. With this approach, unstructured information could be transformed into a structured format. The results of this research show that relevant information can be effectively extracted from Finnish medical reports using classification algorithms with default parameter values. For the detection of breast tumour mentions from medical texts, classifiers achieved high accuracy, almost 90%. Detection of metastasis mentions, however, proved more challenging, with the best-performing models Support Vector Machine (SVM) and logistic regression achieving an F1-score of 81%. The lower performance in metastasis detection is likely due to the more complex problem, ambiguous labeling, and the smaller dataset size. The results of classical classifiers were also compared with FinBERT, a domain-adapted Finnish BERT model. However, classical classifiers outperformed FinBERT. This highlights the challenge of medical language processing when working with minority languages. Moreover, it was noted that parameter tuning based on translated English reports did not significantly improve the detection rates, likely due to linguistic differences between the datasets. This larger translated dataset used for tuning comes from a different clinical domain and employs noticeably simpler, less nuanced language than the Finnish breast cancer reports, which are written by native Finnish-speaking medical experts. This underscores the need for localised datasets and models, particularly for minority languages with unique grammatical structures. Full article

Accurate stock price prediction requires the integration of heterogeneous data streams, yet conventional techniques struggle to simultaneously leverage fine-grained micro-stock features and broader macroeconomic indicators. To address this gap, we propose MambaLLM, a novel framework that fuses macro-index and micro-stock inputs through the synergistic use of state-space models (SSMs) and large language models (LLMs). Our two-branch architecture comprises (i) Micro-Stock Encoder, a Mamba-based temporal encoder for processing granular stock-level data (prices, volumes, and technical indicators), and (ii) Macro-Index Analyzer, an LLM module—employing DeepSeek R1 7B distillation—capable of interpreting market-level index trends (e.g., S&P 500) to produce textual summaries. These summaries are then distilled into compact embeddings via FinBERT. By merging these multi-scale representations through a concatenation mechanism and subsequently refining them with multi-layer perceptrons (MLPs), MambaLLM dynamically captures both asset-specific price behavior and systemic market fluctuations. Extensive experiments on six major U.S. stocks (AAPL, AMZN, MSFT, TSLA, GOOGL, and META) reveal that MambaLLM delivers up to a 28.50% reduction in RMSE compared with suboptimal models, surpassing traditional recurrent neural networks and MAMBA-based baselines under volatile market conditions. This marked performance gain highlights the framework’s unique ability to merge structured financial time series with semantically rich macroeconomic narratives. Altogether, our findings underscore the scalability and adaptability of MambaLLM, offering a powerful, next-generation tool for financial forecasting and risk management. Full article

Financial sentiment analysis is crucial for making informed decisions in the financial markets, as it helps predict trends, guide investments, and assess economic conditions. Traditional methods for financial sentiment classification, such as Support Vector Machines (SVM), Random Forests, and Logistic Regression, served as our baseline models. While somewhat effective, these conventional approaches often struggled to capture the complexity and nuance of financial language. Recent advancements in deep learning, particularly transformer-based models like GPT and BERT, have significantly enhanced sentiment analysis by capturing intricate linguistic patterns. In this study, we explore the application of deep learning for financial sentiment analysis, focusing on fine-tuning GPT-4o, GPT-4o-mini, BERT, and FinBERT, alongside comparisons with traditional models. To ensure optimal configurations, we performed hyperparameter tuning using Bayesian optimization across 100 trials. Using a combined dataset of FiQA and Financial PhraseBank, we first apply zero-shot classification and then fine tune each model to improve performance. The results demonstrate substantial improvements in sentiment prediction accuracy post-fine-tuning, with GPT-4o-mini showing strong efficiency and performance. Our findings highlight the potential of deep learning models, particularly GPT models, in advancing financial sentiment classification, offering valuable insights for investors and financial analysts seeking to understand market sentiment and make data-driven decisions. Full article

With the increase in trading frequency and the growing complexity of data structures, traditional quantitative strategies have gradually encountered bottlenecks in modeling capacity, real-time responsiveness, and multi-dimensional information integration. To address these limitations, a high-frequency signal generation framework is proposed, which integrates graph neural networks, cross-scale Transformer architectures, and macro factor modeling. This framework enables unified modeling of structural dependencies, temporal fluctuations, and macroeconomic disturbances. In predictive validation experiments, the framework achieved a precision of 92.4%, a recall of 91.6%, and an F1-score of 92.0% on classification tasks. For regression tasks, the mean squared error (MSE) and mean absolute error (MAE) were reduced to $1.76\times {10}^{-4}$ and $0.96\times {10}^{-2}$, respectively. These results significantly outperformed several mainstream models, including LSTM, FinBERT, and StockGCN, demonstrating superior stability and practical applicability. Full article

This study investigates the application of large language models (LLMs) in sentiment analysis of financial news and their use in developing effective investment strategies. We conducted sentiment analysis on news articles related to the top 30 companies listed on Nasdaq using both discriminative models such as BERT and FinBERT, and generative models including Llama 3.1, Mistral, and Gemma 2. To enhance the robustness of the analysis, advanced prompting techniques—such as Chain of Thought (CoT), Super In-Context Learning (SuperICL), and Bootstrapping—were applied to generative LLMs. The results demonstrate that long strategies generally yield superior portfolio performance compared to short and long–short strategies. Notably, generative LLMs outperformed discriminative models in this context. We also found that the application of SuperICL to generative LLMs led to significant performance improvements, with further enhancements noted when both SuperICL and Bootstrapping were applied together. These findings highlight the profitability and stability of the proposed approach. Additionally, this study examines the explainability of LLMs by identifying critical data considerations and potential risks associated with their use. The research highlights the potential of integrating LLMs into financial strategy development to provide a data-driven foundation for informed decision-making in financial markets. Full article

This study combines a theoretical and empirical approach to analyze the transition from corporate social responsibility to corporate sustainability in Spanish tourism companies, with an emphasis on the integration of ESG (environmental, social, and governance) criteria. In the theoretical domain, a computational literature review is conducted by applying topic modeling to 1505 scientific documents published between 2004 and 2023, identifying key trends and evaluating the evolution from CSR to CS. In the empirical domain, 364 corporate reports published between 2010 and 2021 are analyzed, using text mining techniques to examine changes in the relative frequency of terms associated with CSR and CS, and the BERTopic model to detect key management areas. Additionally, the FinBERT model classifies the content of the reports into nine ESG categories, quantifying their relevance across different tourism subsectors. The results confirm a progressive transition towards CS, evidenced by shifts in thematic priorities reflected in the literature and a significant increase in the use of terms associated with CS in corporate reports. The research provides valuable insights for managers, regulators, and local communities, enabling the design of strategies better aligned with ESG standards, optimizing business management, and strengthening sustainability in the Spanish tourism sector. Full article

GPT (Generative Pre-trained Transformer) is a groundbreaking generative model that has facilitated substantial progress in natural language processing (NLP). As the GPT-n series has continued to evolve, its applications have garnered considerable attention across various industries, particularly in finance. In contrast, traditional financial research has primarily focused on analyzing structured data such as stock prices. However, recent trends highlight the growing importance of natural language techniques that address unstructured factors like investor sentiment and the impact of news. Positive or negative information about specific companies, industries, or the overall economy found in news or social media can influence investor behavior and market volatility, highlighting the critical need for robust sentiment analysis. In this context, we utilize the state-of-the-art language model GPT and the finance-specific sentiment analysis model FinBERT to perform sentiment and time-series analyses on financial news data, comparing the performance of the two models to demonstrate the potential of GPT. Furthermore, by examining the relationship between sentiment shifts in financial markets and news events, we aim to provide actionable insights for investment decision-making, emphasizing both the performance and interpretability of the models. To enhance the performance of GPT-4o, we employed a systematic approach to prompt design and optimization. This process involved iterative refinement, guided by insights derived from a labeled dataset. This approach emphasized the pivotal importance of prompt design in improving model accuracy, resulting in GPT-4o achieving higher performance than FinBERT. During the experiment phase, sentiment scores were generated from New York Times news data and visualized through time-series graphs for both models. Although both models exhibited similar trends, significant differences arose depending on news content characteristics across categories. According to the results, the performance of GPT-4o, optimized through prompt engineering, outperformed that of FinBERT by up to 10% depending on the sector. These findings emphasize the importance of prompt engineering and demonstrate GPT-4o’s potential to improve sentiment analysis. Furthermore, the categorized news data approach suggests potential applications in predicting the outlook of categorized financial products. Full article

This study compares three machine learning and deep learning models—Support Vector Regression (SVR), Recurrent Neural Networks (RNN), and Long Short-Term Memory (LSTM)—for predicting market prices using the NGX All-Share Index dataset. The models were evaluated using multiple error metrics, including Mean Absolute Error (MAE), Mean Squared Error (MSE), Root Mean Square Error (RMSE), Mean Percentage Error (MPE), and R-squared. RNN and LSTM were tested with both 30 and 60-day windows, with performance compared to SVR. LSTM delivered better R-squared values, with a 60-day LSTM achieving the best accuracy (R-squared = 0.993) when using a combination of endogenous market data and technical indicators. SVR showed reliable results in certain scenarios but struggled in fold 2 with a sudden spike that shows a high probability of not capturing the entire underlying NGX pattern in the dataset correctly, as witnessed by the high validation loss during the period. Additionally, RNN faced the vanishing gradient problem that limits its long-term performance. Despite challenges, LSTM’s ability to handle temporal dependencies, especially with the inclusion of On-Balance Volume, led to significant improvements in prediction accuracy. The use of the Optuna optimisation framework further enhanced model training and hyperparameter tuning, contributing to the performance of the LSTM model. Full article

Accurately predicting stock prices remains a challenging task due to the volatile and complex nature of financial markets. In this study, we propose a novel hybrid deep learning framework that integrates a large language model (LLM), a Linear Transformer (LT), and a Convolutional Neural Network (CNN) to enhance stock price prediction using solely historical market data. The framework leverages the LLM as a professional financial analyst to perform daily technical analysis. The technical indicators, including moving averages (MAs), relative strength index (RSI), and Bollinger Bands (BBs), are calculated directly from historical stock data. These indicators are then analyzed by the LLM, generating descriptive textual summaries. The textual summaries are further transformed into vector representations using FinBERT, a pre-trained financial language model, to enhance the dataset with contextual insights. The FinBERT embeddings are integrated with features from two additional branches: the Linear Transformer branch, which captures long-term dependencies in time-series stock data through a linearized self-attention mechanism, and the CNN branch, which extracts spatial features from visual representations of stock chart data. The combined features from these three modalities are then processed by a Feedforward Neural Network (FNN) for final stock price prediction. Experimental results on the S&P 500 dataset demonstrate that the proposed framework significantly improves stock prediction accuracy by effectively capturing temporal, spatial, and contextual dependencies in the data. This multimodal approach highlights the importance of integrating advanced technical analysis with deep learning architectures for enhanced financial forecasting. Full article

This study explores the comparative performance of cutting-edge AI models, i.e., Finaance Bidirectional Encoder representations from Transsformers (FinBERT), Generatice Pre-trained Transformer GPT-4, and Logistic Regression, for sentiment analysis and stock index prediction using financial news and the NGX All-Share Index data label. By leveraging advanced natural language processing models like GPT-4 and FinBERT, alongside a traditional machine learning model, Logistic Regression, we aim to classify market sentiment, generate sentiment scores, and predict market price movements. This research highlights global AI advancements in stock markets, showcasing how state-of-the-art language models can contribute to understanding complex financial data. The models were assessed using metrics such as accuracy, precision, recall, F1 score, and ROC AUC. Results indicate that Logistic Regression outperformed the more computationally intensive FinBERT and predefined approach of versatile GPT-4, with an accuracy of 81.83% and a ROC AUC of 89.76%. The GPT-4 predefined approach exhibited a lower accuracy of 54.19% but demonstrated strong potential in handling complex data. FinBERT, while offering more sophisticated analysis, was resource-demanding and yielded a moderate performance. Hyperparameter optimization using Optuna and cross-validation techniques ensured the robustness of the models. This study highlights the strengths and limitations of the practical applications of AI approaches in stock market prediction and presents Logistic Regression as the most efficient model for this task, with FinBERT and GPT-4 representing emerging tools with potential for future exploration and innovation in AI-driven financial analytics. Full article

In the current era, the environmental component of ESG is recognized as a major driver due to the pressing challenges posed by climate change, population growth, global warming, and shifting weather patterns. The environment must be considered a critical factor, and as evidenced by existing research, it is regarded as the dominant component within ESG. In this study, the ESG score is derived primarily from the environmental score. The increasing importance of the environmental, social, and governance (ESG) factors in financial markets, along with the growing need for sentiment analysis in sustainability, has necessitated the development of advanced sentiment analysis techniques. A predictive model has been introduced utilizing a nested sentiment analysis framework, which classifies sentiments towards eco-friendly and non-eco-friendly products, as well as positive and negative sentiments, using FinBERT. The model has been optimized with the AdamW optimizer, L2 regularization, and dropout to assess how sentiments related to these product types influence ESG metrics. The “black-box” nature of the model has been addressed through the application of explainable AI (XAI) to enhance its interpretability. The model demonstrated an accuracy of 91.76% in predicting ESG scores and 99% in sentiment classification. The integration of XAI improves the transparency of the model’s predictions, making it a valuable tool for decision-making in making sustainable investments. This research is aligned with the United Nations’ Sustainable Development Goals (SDG 12 and SDG 13), contributing to the promotion of sustainable practices and fostering improved market dynamics. Full article

Accurately predicting financial entity performance remains a challenge due to the dynamic nature of financial markets and vast unstructured textual data. Financial knowledge graphs (FKGs) offer a structured representation for tackling this problem by representing complex financial relationships and concepts. However, constructing a comprehensive and accurate financial knowledge graph that captures the temporal dynamics of financial entities is non-trivial. We introduce FintechKG, a comprehensive financial knowledge graph developed through a three-dimensional information extraction process that incorporates commercial entities and temporal dimensions and uses a financial concept taxonomy that ensures financial domain entity and relationship extraction. We propose a temporal and relational graph convolutional network (RGCN)-based representation for FintechKG data across multiple timesteps, which captures temporal dependencies. This representation is then combined with FinBERT embeddings through a projection layer, enabling a richer feature space. To demonstrate the efficacy of FintechKG, we evaluate its performance using the example task of financial performance prediction. A logistic regression model uses these combined features and social media embeddings for performance prediction. We classify whether the revenue will increase or decrease. This approach demonstrates the effectiveness of FintechKG combined with textual information for accurate financial forecasting. Our work contributes a systematic FKG construction method and a framework that utilizes both relational and textual embeddings for improved financial performance prediction. Full article

The aim of this study is to investigate the potential of ChatGPT in analyzing the financial sentiment analysis of entrepreneurs. Sentiment analysis involves detecting if it is positive, negative, or neutral from a text. We examine several prompts on ChatGPT-4, ChatGPT-4.0, and LeChat-Mistral and compare the results with FinBERT. Then, we examine the correlation between scores given by both tools with the type, size, and age of the company. The results have shown that scores given by FinBERT are mostly significant and positively correlated with sustainable variables. By sharing these results, we hope to stimulate future research and advances in the field of financial services, particularly bank loans. Full article

Economic and financial narratives inform market sentiment through the emotions that are triggered and the subjectivity that gets evoked. There is an important connection between narrative, sentiment, and human decision making. In this study, natural language processing is used to extract market sentiment from the narratives using FinBERT, a Python library that has been pretrained on a large financial corpus. A news sentiment index is constructed and shown to be a leading indicator of systemic risk. A rolling regression shows how the impact of news sentiment on systemic risk changes over time, with the importance of news sentiment increasing in more recent years. Monitoring systemic risk is an important tool used by central banks to proactively identify and manage emerging risks to the financial system; it is also a key input into the credit loss provision quantification at banks. Credit loss provision is a key focus area for auditors because of the risk of material misstatement, but finding appropriate sources of audit evidence is challenging. The causal relationship between news sentiment and systemic risk suggests that news sentiment could serve as an early warning signal of increasing credit risk and an effective indicator of the state of the economic cycle. The news sentiment index is shown to be useful as audit evidence when benchmarking trends in accounting provisions, thus informing financial disclosures and serving as an exogenous variable in econometric forecast models. Full article

Cryptocurrencies are becoming increasingly prominent in financial investments, with more investors diversifying their portfolios and individuals drawn to their ease of use and decentralized financial opportunities. However, this accessibility also brings significant risks and rewards, often influenced by news and the sentiments of crypto investors, known as crypto signals. This paper explores the capabilities of large language models (LLMs) and natural language processing (NLP) models in analyzing sentiment from cryptocurrency-related news articles. We fine-tune state-of-the-art models such as GPT-4, BERT, and FinBERT for this specific task, evaluating their performance and comparing their effectiveness in sentiment classification. By leveraging these advanced techniques, we aim to enhance the understanding of sentiment dynamics in the cryptocurrency market, providing insights that can inform investment decisions and risk management strategies. The outcomes of this comparative study contribute to the broader discourse on applying advanced NLP models to cryptocurrency sentiment analysis, with implications for both academic research and practical applications in financial markets. Full article