Financial Datasets Research Articles

Research on Financial Market Prediction Model Based on Big Data and Quantum Computing

A financial market is a trading system for financial assets such as derivatives, stocks, currencies, and bonds. Financial markets, which can be virtual or physical, are essential to the world economy. Financial forecasting has become an enormous difficulty due to the markets’ quick internationalization and the volume of data gathered from various sources growing at an accelerating rate. The study explores the creation of a model for stock market forecasting that leverages the power of big data analytics and quantum computing (QC). By handling multifaceted datasets and achieving high-accuracy forecasting, big data and QC improve market trends and insights. This is achieved by leveraging QC speed-driven problem-solving capabilities. In this study, we proposed a novel Hippopotamus Optimized Quantum Refined Support Vector Machine (HO-QRSVM) to predict the financial market. The financial dataset came from several places, such as economic databases and stock exchanges. The preprocessed data from the acquired data were cleaned and normalized. To remove dimensionality and extract features from preprocessed data, principle component analysis (PCA) is used. The capacity of QC to handle entanglement and superposition enables the simultaneous investigation of several potential market situations, leading to faster convergence and more precise forecasts. The result demonstrated the proposed method has significant improvements in prediction accuracy compared to other traditional algorithms. The performance evaluation techniques include the F1-score (96.3%), recall (98.2%), accuracy (98.5%), and precision (98.3%). The research, big data analytics, and QC combined can greatly improve financial market forecasts, giving decision-makers and strategic investors an advantage over their competition.

E2CNN: entity-type-enriched cascaded neural network for Chinese financial relation extraction

Knowledge Graphs (KGs) are pivotal for effectively organizing and managing structured information across various applications. Financial KGs have been successfully employed in advancing applications such as audit, anti-fraud, and anti-money laundering. Despite their success, the construction of Chinese financial KGs has seen limited research due to the complex semantics. A significant challenge is the overlap triples problem, where entities feature in multiple relations within a sentence, hampering extraction accuracy–more than 39% of the triples in Chinese datasets exhibit the overlap triples. To address this, we propose the Entity-type-Enriched Cascaded Neural Network (E2CNN), leveraging special tokens for entity boundaries and types. E2CNN ensures consistency in entity types and excludes specific relations, mitigating overlap triple problems and enhancing relation extraction. Besides, we introduce the available Chinese financial dataset FinCorpus.CN, annotated from annual reports of 2,000 companies, containing 48,389 entities and 23,368 triples. Experimental results on the DUIE dataset and FinCorpus.CN underscore E2CNN’s superiority over state-of-the-art models.

MM-iTransformer: A Multimodal Approach to Economic Time Series Forecasting with Textual Data

This paper introduces a novel multimodal framework for economic time series forecasting, integrating textual information with historical price data to enhance predictive accuracy. The proposed method employs a multi-head attention mechanism to dynamically align textual embeddings with temporal price data, capturing previously unrecognized cross-modal dependencies and enhancing the model’s ability to interpret event-driven market dynamics. This enables the framework to model complex market behaviors in a unified and effective manner. Experimental results across multiple financial datasets, including the foreign exchange (Forex) and Gold-price datasets, demonstrate that incorporating textual information significantly enhances forecasting accuracy. Compared to models relying solely on historical price data, the proposed framework achieves a substantial reduction in Mean Squared Error (MSE) loss, with improvements of up to 26.79%. This highlights the effectiveness of leveraging textual inputs alongside structured time series data in capturing complex market dynamics and improving predictive performance.

Predicting financial distress in high-dimensional imbalanced datasets: a multi-heterogeneous self-paced ensemble learning framework

Financial distress prediction (FDP) is a critical area of study for researchers, industry stakeholders, and regulatory authorities. However, FDP tasks present several challenges, including high-dimensional datasets, class imbalances, and the complexity of parameter optimization. These issues often hinder the predictive model’s ability to accurately identify companies at high risk of financial distress. To mitigate these challenges, we introduce FinMHSPE—a novel multi-heterogeneous self-paced ensemble (MHSPE) FDP learning framework. The proposed model uses pairwise comparisons of data from multiple time frames combined with the maximum relevance and minimum redundancy method to select an optimal subset of features, effectively resolving the high dimensionality issue. Furthermore, the proposed framework incorporates the MHSPE model to iteratively identify the most informative majority class data samples, effectively addressing the class imbalance issue. To optimize the model’s parameters, we leverage the particle swarm optimization algorithm. The robustness of our proposed model is validated through extensive experiments performed on a financial dataset of Chinese listed companies. The empirical results demonstrate that the proposed model outperforms existing competing models in the field of FDP. Specifically, our FinMHSPE framework achieves the highest performance, achieving an area under the curve (AUC) value of 0.9574, considerably surpassing all existing methods. A comparative analysis of AUC values further reveals that FinMHSPE outperforms state-of-the-art approaches that rely on financial features as inputs. Furthermore, our investigation identifies several valuable features for enhancing FDP model performance, notably those associated with a company’s information and growth potential.

Assessing the Performance of the MARFIMA Model Using Simulated and Real Life Data

A modified autoregressive fractional integrated moving average MARFIMA (p, d, q) is presented in this study to describe time series data that are nonstationary and have a fractional difference value of 1<d<1.5. Data from ARFIMA simulations are used to assess the performance of the MARFIMA model. The autoregressive fractional integrated moving average ARFIMA model and the MARFIMA model's performance were also compared in a number of applications. Using the Akaike Information Criterion (AIC), Schwartz Bayesian Information Criterion (SBIC), root mean square error (RMSE), and normalized mean square error (NMSE), the best model was chosen, and its performance was evaluated using a variety of forecast accuracy metrics. Results indicated that across four distinct financial and economic data sets, which include the price of crude oil, the Nigerian stock market, the Nigerian all-shares index, and the Nigerian food and beverage index, the MARFIMA model performed better than the ARFIMA model. The research provides a more robust method for modeling and forecasting long memory data. The study has also contributed to existing literature on the most appropriate method for modelling long memory associated with financial and economic data.

RL4CEP: reinforcement learning for updating CEP rules

This paper presents RL4CEP, a reinforcement learning (RL) approach to dynamically update complex event processing (CEP) rules. RL4CEP uses Double Deep Q-Networks to update the threshold values used by CEP rules. It is implemented using Apache Flink as a CEP engine and Apache Kafka for message distribution. RL4CEP is a generic approach for scenarios in which CEP rules need to be updated dynamically. In this paper, we use RL4CEP in a financial trading use case. Our experimental results based on three financial trading rules and eight financial datasets demonstrate the merits of RL4CEP in improving the overall profit, when compared to baseline and state-of-the-art approaches, with a reasonable consumption of resources, i.e., RAM and CPU. Finally, our experiments indicate that RL4CEP is executed quite fast compared to traditional CEP engines processing static rules.

Comparative Analysis of Currency Exchange and Stock Markets in BRICS Using Machine Learning to Forecast Optimal Trends for Data-Driven Decision Making

The BRICS nations’ economies show that the countries are global financial powerhouses whose currency exchange rates and stock markets have influence globally. In this paper, the analysis of the forecast trends in both Currency Exchange and Stock Markets using a dual layered machine learning approach exposing models such as Long Short Term Memory (LSTM), Random Forest, Gradient Boosting and Support vector machines (SVM) is conducted. Their performance is tested twice, first on currency exchange and then on stock market data, to compare them on the basis of predictive power to deliver actionable insights. Each model is applied to currency and stock market data, separately, as the study mainly uses extensive historical datasets from BRICS economies. Benchmarking is done using metrics such as Mean Absolute Error (MAE), Root Mean Square Error (RMSE) and R-squared values. For currency exchange, LSTM turned out to be the most effective model as it can handle a sequence of time series data. The best performance for stock market forecasting was achieved by Gradient Boosting, which is adept at finding complex nonlinear relationships. Random Forest proved to be consistent across both Datasets but SVM was found to be challenged on Scalability and Data Complexity, with relatively lower accuracy. The research goes on to repeat the comparative analysis for each of the different models, to illustrate the subtle differences between machine learning techniques in their capacity to effectively process financial datasets of all varieties. Predictive accuracy and reliability is further enhanced to reconcile conflicting trends between currency and stock markets by creating an ensemble model of all algorithms. These findings provide a robust framework for informed decision making for stakeholders to identify the more stable and hence more profitable market in the BRICS context. The results of this study add to the expansion of application of machine learning to global finance by demonstrating how tailored algorithms can offer significant economic planning and investment strategy plans.

Neutrosophic Sets in Big Data Analytics: A Novel Approach for Feature Selection and Classification

Big Data Analytics are said to help in transforming huge amounts of raw data towards valuable information that can be used, but there are formidable challenges in feature selection and classification due to the complexity and high dimensionality of the data. Traditional methods are usually too weak to handle the built-in uncertainty, imprecision, and inconsistency within big data and they often fail to perform well. This paper aims to induce the new methodology on these problems using the sets of neutrosophic in dealing with more flexible and nuanced data analysis. The key contributions to the current approach proposed are threefold. First, generalization of the classical set through extension of the notions of truth, indeterminacy, and falsity by allowing representations of uncertainty in data. The second combines a powerful process for selecting features based upon neutrosophic set theory that is optimal by genetic algorithms and advances a step further by applying these features in training and validating the classification models across a set of different domains. Therefore, the major aim from this study is to increase accuracy and reliability in feature selection and classification in big data analytics. This methodology has been implemented and tested over datasets of the following types: healthcare, finance, social media, and more. Results have proved great improvement against conventional performance metrics, for example, the classification accuracy with an SVM classifier over the Cleveland Heart Disease dataset increases from 83.5% to 87.2%, and of a Random Forest classifier over a financial dataset from 76.4% to 81.9%. For instance, the accuracy of social media sentiment analysis changed to 82.7% from 78.3%. All these findings establish that the neutrosophic set-based method holds good advantages in addressing the limitations of classical alternatives. The proposed approach of neutrosophism, through an explicit model, enhances performances in classifications and, at the same time, augments overall robustness and reliability in big data analytic. The importance of this study lies in establishing the groundwork for further research and practical applications, thus indicating possible further development in this field.

Comprehensive Analysis of Stock Price Dynamics Using Ensemble Machine Learning Models for Enhanced Prediction Accuracy

Stock price prediction is an important component of the financial analysis because the results influence the increase in economic growth and investment. This work aims to develop an ensemble SL technique that consists of mainly PCA, PSO, and SVM to achieve better prediction. Hence, through PCA, large numbers of stocked data dimensions are compressed without compromising on the crucial feature of data set. The problem of parameter selection for non-linear datasets is handled by using a bio-inspired optimization technique known as PSO in order to optimize the SVM hyperparameters. As the core accurate predictor model, the SVM employs the Radial Basis Function to provide the substantial regression capacity for sophisticated financial data sets. The ensemble framework was used with actual stock price data and the information set into training and testing sets. The acknowledgement of probable manifold values indicated that the proposed approach is more accurate than conventional approaches, with an accuracy rate of 95.5 %, when benchmarked using RMSE or MAE. In particular, the forecasts of stock prices by integrating PCA for feature reduction and PSO for parameter tuning with SVM regression is a notable improvement. The proposed methodology can be easily applied to scale for financial analytics since it manages to solve for the issues of noisy and non-linear high dimensional data.

Optimized Hybrid Machine Learning Approaches for Stock Market Forecasting and Time Series Analysis

The research introduces an innovative hybrid model of KPCA, ESVM, and TLBO to analyze stock price variation and time series forecasting. To handle the issue of high dimensionality of the financial data and the nonlinear dependencies amongst the variables, the model employs KPCA for feature extraction, thus identifying, and retaining only the feature space that is most relevant. Subsequently, the features extracted are passed through ESVM for regression – aiding in correct estimations on stock prices. To improve the outcome, prediction accuracy and to fine transient parameters of the model TLBO as a metaheuristic algorithm is used. The application of KPCA-ESVM-TLBO establishes optimal characteristics from the above methodologies, producing efficiency in tackling complications and nonlinearity of the data structures. KPCA looks for hidden structure; ESVM does regression with the kernel; and TLBO twiddles appropriate knobs such as λ and kernel coefficients. By using real-world financial data sets, the experimental evaluations presented show that the reported method outperforms the conventional benchmarks in relations of predictive accuracy. MAE, RMSE, and accuracy confirm its relevance: predictive accuracy of 99.99%. This approach to using artificial neural networks in tandem with a nearest neighbor algorithm presents the prospect of a potent weapon for forecasting and decision making in ever complex and volatile market.

Machine Learning Solutions for Predicting Stock Trends in BRICS amid Global Economic Shifts and Decoding Market Dynamics

In this paper we examine the role of machine learning (ML) in predicting stock market trends within BRICS economies. Complex, interdependent global and regional economic factors are today and will in the future increasingly influence stock markets, which necessitates innovative techniques for trend analysis. Using this state of the art ML models Support Vector Machines (SVMs), Random Forests, and neural networks the study predicts market fluctuations based on historical stock data, economic indicators and geopolitical events. This research emphasizes the increasing role of deep learning, especially with models such as Transformers and LSTMs, to meet the demand for high accuracy predictive systems in the volatile market. Its analysis brings model performance into comparison of BRICS nations, taking into account the peculiar financial and economic behavior peculiar to each of them. These results illuminate how ML can provide actionable intelligence for investors and policymakers to better manage risk and better make strategic investments. Findings from the study underscore the requirement for adopting sophisticated data driven tools in order to negotiate the intricacies of globalized financial systems. This study also explains the basis in helping us understand how machine learning changes the perspective on stock market analysis. It is a great source to understand how different ML techniques such as Support Vector Machines which are good at classification problems and Random Forests, which are known to handle over fitting, can be used on a financial dataset. It shows cutting edge tools for market prediction such as deep learning models like LSTMs, which are able to handle sequential time series data, or Transformers that further improve the traditional architectures with attention mechanisms. The paper also discusses data preprocessing methods, such as feature engineering and normalization, and the importance of their inclusion in improving model performance. This research shows the value of ML literacy and provides future financial analysts and decision makers with tools for addressing market volatility in a data driven and strategic context.

GDSMOTE: A Novel Synthetic Oversampling Method for High-Dimensional Imbalanced Financial Data

Synthetic oversampling methods for dealing with imbalanced classification problems have been widely studied. However, the current synthetic oversampling methods still cannot perform well when facing high-dimensional imbalanced financial data. The failure of distance measurement in high-dimensional space, error accumulation caused by noise samples, and the reduction of recognition accuracy of majority samples caused by the distribution of synthetic samples are the main reasons that limit the performance of current methods. Taking these factors into consideration, a novel synthetic oversampling method is proposed, namely the gradient distribution-based synthetic minority oversampling technique (GDSMOTE). Firstly, the concept of gradient contribution was used to assign the minority-class samples to different gradient intervals instead of relying on the spatial distance. Secondly, the root sample selection strategy of GDSMOTE avoids the error accumulation caused by noise samples and a new concept of nearest neighbor was proposed to determine the auxiliary samples. Finally, a safety gradient distribution approximation strategy based on cosine similarity was designed to determine the number of samples to be synthesized in each safety gradient interval. Experiments on high-dimensional imbalanced financial datasets show that GDSMOTE can achieve a higher F1-Score and MCC metrics than baseline methods while achieving a higher recall score. This means that our method has the characteristics of improving the recognition accuracy of minority-class samples without sacrificing the recognition accuracy of majority-class samples and has good adaptability to data decision-making tasks in the financial field.

Contrastive Unsupervised Graph Neural Network in Financial Industry

This paper explores the application of the Contrastive Unsupervised Graph Neural Network (CuGNN) framework in financial domains, leveraging its heterophily-based adaptive convolution to address critical tasks like fraud detection, risk propagation, and portfolio optimization. CuGNN's ability to identify and utilize heterophilic patterns in financial transaction graphs enables robust representation learning even in unsupervised settings, where labeled data is scarce. Specifically, we adapt CuGNN to model risk spread across trading and investment networks by dynamically capturing high-frequency and low-frequency signals through its adaptive convolution mechanism. This approach allows us to differentiate between correlated and inverse-correlated asset behaviors, providing deeper insights into systemic risks and diversification strategies. Furthermore, CuGNN’s feature-distribution embedding and latent-space contrastive learning strategies are utilized to detect anomalous interactions in high-frequency trading networks and to identify heterophilic relationships in credit scoring and supply chain finance. By applying the CuGNN framework across diverse financial datasets, this study demonstrates its potential to uncover hidden structures and optimize decision-making in critical financial applications, addressing the growing need for explainable and adaptive graph-based methods in the sector.

PENGARUH KUALITAS AUDIT, KEKUATAN PENDAPATAN, DAN UKURAN PERUSAHAAN TERHADAP NILAI PERUSAHAAN

Increasing the welfare of capital owners or company owners is one of the company's goals, which can be done by increasing firm value. This research aims to test audit quality, earnings power and firm size on the value of companies in the health services industry listed on the Indonesia Stock Exchange between 2019 and 2022. The research model uses a causality design and uses multiple linear regression analysis with sources. secondary data. The sampling technique used was purposive sampling, which included a total of 13 companies and 52 sets of financial report data from the health industry during the period 2019 to 2022. The findings of this research show that the combination of audit quality, firm size and earnings power simultaneously influences firm value. Audit quality does not partially influence firm value, while firm size and earnings power partially influence firm value.

Chain-structured neural architecture search for financial time series forecasting

AbstractNeural architecture search (NAS) emerged as a way to automatically optimize neural networks for a specific task and dataset. Despite an abundance of research on NAS for images and natural language applications, similar studies for time series data are lacking. Among NAS search spaces, chain-structured are the simplest and most applicable to small datasets like time series. We compare three popular NAS strategies on chain-structured search spaces: Bayesian optimization (specifically Tree-structured Parzen Estimator), the hyperband method, and reinforcement learning in the context of financial time series forecasting. These strategies were employed to optimize simple well-understood neural architectures like the MLP, 1D CNN, and RNN, with more complex temporal fusion transformers (TFT) and their own optimizers included for comparison. We find Bayesian optimization and the hyperband method performing best among the strategies, and RNN and 1D CNN best among the architectures, but all methods were very close to each other with a high variance due to the difficulty of working with financial datasets. We discuss our approach to overcome the variance and provide implementation recommendations for future users and researchers.

A hybrid machine learning model with self-improved optimization algorithm for trust and privacy preservation in cloud environment

The rapid adoption of cloud-based data sharing is transforming collaboration across various sectors, yet ensuring trust and privacy in sensitive data remains a critical challenge. This paper presents a hybrid model aimed at enhancing data privacy and trust in cloud environments, specifically addressing concerns in healthcare and finance. The model combines k-anonymity for user privacy, an optimized Firefly algorithm for trust generation, and a Time-aware Modified Best Fit Decreasing (T-MBFD) algorithm to improve resource allocation efficiency. Key contributions include a comprehensive methodology that encompasses dataset selection, preprocessing, model training, and evaluation across multiple datasets, including healthcare, financial, and pandemic-related data. Experimental results demonstrate that the hybrid model achieves a precision score of approximately 90% and an accuracy of around 93% in financial datasets, significantly outperforming existing methods in both privacy preservation and computational efficiency. These findings emphasize the model’s effectiveness in securely facilitating data-driven collaboration in highly regulated domains, thus paving the way for practical applications that uphold individual privacy and data integrity in cloud-based environments.

Enhancing financial risk prediction with symbolic classifiers: addressing class imbalance and the accuracy–interpretability trade–off

Machine learning for financial risk prediction has garnered substantial interest in recent decades. However, the class imbalance problem and the dilemma of accuracy gain by loss interpretability have yet to be widely studied. Symbolic classifiers have emerged as a promising solution for forecasting banking failures and estimating creditworthiness as it addresses class imbalance while maintaining both accuracy and interpretability. This paper aims to evaluate the effectiveness of REMED, a symbolic classifier, in the context of financial risk management, and focuses on its ability to handle class imbalance and provide interpretable decision rules. Through empirical analysis of a real-world imbalanced financial dataset from the Federal Deposit Insurance Corporation, we demonstrate that REMED effectively handles class imbalance, improving performance accuracy metrics while ensuring interpretability through a concise and easily understandable rule system. A comparative analysis is conducted against two well-known rule-generating approaches, J48 and JRip. The findings suggest that, with further development and validation, REMED can be implemented as a competitive approach to improve predictive accuracy on imbalanced financial datasets without compromising model interpretability.

Export effects of overseas patent applications by Korean SMEs

ABSTRACT This study analyzed the impact of overseas patent applications by Korean companies, particularly focusing on small and medium-sized enterprises (SMEs), on their export performance, utilizing data from 1999 to 2019. We integrated the Documentation Database patent dataset from the EPO with the Korean financial dataset. The fundamental hypothesis of this study is that, unlike large enterprises (LEs), SMEs find the cost of filing and maintaining patents overseas burdensome. Consequently, they tend to file patents primarily in their key export markets rather than in major global markets, which implies that, in contrast to LEs, the patent applications of SMEs may positively impact exports only to the specific countries where they have filed. The key findings are as follows. Firstly, unlike LEs, SMEs tend to export specifically to the countries where they have filed. These results demonstrate how firms’ behavior can vary depending on the heterogeneity in firm size. Secondly, the effect of overseas patents filed by Korean SMEs is most pronounced for the ASEAN countries. Based on these insights, we recommend the implementation of policy measures such as providing financial support to cover the costs of overseas patent applications for SMEs.

Boosting Financial Market Prediction Accuracy With Deep Learning and Big Data

The accuracy of financial market trend prediction directly impacts investors' decisions and financial institutions' risk management, making it a focal point of research in the financial domain. While traditional statistical methods lay the foundation for market forecasting, they still face limitations in handling complex, nonlinear, and non-stationary financial time series data with accuracy and adaptability. Time series analysis plays a pivotal role in financial market prediction, revealing historical patterns and future trends within the data. Addressing the limitations of existing methods, this study proposes a deep learning-based CEEMDAN-CNN-LSTM model. Leveraging the CEEMDAN decomposition method to capture the multi-frequency components of time series, CNN extracts spatial features, and LSTM learns temporal dependencies. Experimental results demonstrate that the performance of the CEEMDAN-CNN-LSTM model surpasses traditional models on standardized evaluation metrics such as RMSE, MAE, and MAPE across four major financial datasets.

Transform Financial Data into Strategic Insights Using the Sap Business Technology Platform

This article examines the groundbreaking fusion of SAP Business Technology Platform (BTP) and Artificial Intelligence (AI) in the realm of financial reporting, emphasizing their transformative role in translating financial data into strategic insights for executive leadership. By introducing automated commentary generation, this integration enables BTP to convert intricate financial datasets into coherent narratives that furnish decision-makers with actionable intelligence. Positioned at the nexus of AI progress and financial analysis, BTP facilitates the seamless conversion of complex data into narrative or commentary reports, fostering coherence, insightfulness, and accessibility for decision-makers. The discourse delves into the underlying mechanisms of BTP functionality in financial reporting, spanning data interpretation, language processing, commentary generation, and customization, thereby enhancing report efficiency, precision, and accessibility. Through meticulous exploration, this article elucidates BTP's contributions to financial reporting commentary, including enhanced efficiency, accuracy, scalability, and personalized delivery of financial insights. Furthermore, it confronts the challenges inherent in BTP application, encompassing technical intricacies, ethical considerations, and the constraints of current technologies in capturing financial intricacies. Looking ahead, the article envisions a future where ongoing advancements in AI and machine learning refine BTP capabilities, furnishing even more sophisticated and nuanced financial insights to underpin strategic decision-making at the highest echelons of business leadership.