Category Ranking
98%
Total Visits
921
Avg Visit Duration
2 minutes
Citations
20
Article Abstract
The diverse characteristics of heterogeneous data pose challenges in analyzing combined price and volume data. Therefore, appropriately handling heterogeneous financial data is crucial for accurate stock prediction. This article proposes a model that applies customized data processing methods tailored to the characteristics of different types of heterogeneous financial data, enabling finer granularity and improved feature extraction. By utilizing the structured multi-head attention mechanism, the model captures the impact of heterogeneous financial data on stock price trends by extracting data information from technical, financial, and sentiment indicators separately. Experimental results conducted on four representative individual stocks in China's A-share market demonstrate the effectiveness of the proposed method. The model achieves an average MAPE of 1.378%, which is 0.429% lower than the benchmark algorithm. Moreover, the backtesting return rate exhibits an average increase of 28.56%. These results validate that the customized preprocessing method and structured multi-head attention mechanism can enhance prediction accuracy by attending to different types of heterogeneous data individually.
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC10703059 | PMC |
| http://dx.doi.org/10.7717/peerj-cs.1653 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
The burden of dengue fever in travellers: a systematic literature review.
New Microbes New Infect
October 2025
Takeda Pharmaceuticals International AG, Zurich, Switzerland.
Background: Dengue is a mosquito-borne viral infection with growing global impact, including international travellers travelling to and from endemic regions. This systematic literature review aimed to assess the clinical and economic burden of dengue in travellers from non-endemic countries.
Methods: This systematic review was conducted following the PRISMA guidelines to assess the incidence, prevalence, mortality, healthcare resource use, and costs of dengue fever in travellers between non-endemic and endemic regions.
Viral warfare: unleashing engineered oncolytic viruses to outsmart cancer's defenses.
Front Immunol
September 2025
Department of Pathological Sciences, School of Veterinary Medicine, Louisiana State University, Baton Rouge, LA, United States.
Oncolytic virotherapy (OVT) has emerged as a promising and innovative cancer treatment strategy that harnesses engineered viruses to selectively infect, replicate within, and destroys malignant cells while sparing healthy tissues. Beyond direct oncolysis, oncolytic viruses (OVs) exploit tumor-specific metabolic, antiviral, and immunological vulnerabilities to reshape the tumor microenvironment (TME) and initiate systemic antitumor immunity. Despite promising results from preclinical and clinical studies, several barriers, including inefficient intratumoral virus delivery, immune clearance, and tumor heterogeneity, continue to limit the therapeutic advantages of OVT as a standalone modality and hindered its clinical success.
View Article and Find Full Text PDFIntegrative profiling of lung cancer biomarkers EGFR, ALK, KRAS, and PD-1 with emphasis on nanomaterials-assisted immunomodulation and targeted therapy.
Front Immunol
September 2025
Department of Thoracic Surgery, Shenzhen People's Hospital (The First Affiliated Hospital, Southern University of Science and Technology; The Second Clinical Medical College, Jinan University), Shenzhen, Guangdong, China.
Background: Lung cancer remains the leading cause of cancer-related mortality globally, primarily due to late-stage diagnosis, molecular heterogeneity, and therapy resistance. Key biomarkers such as EGFR, ALK, KRAS, and PD-1 have revolutionized precision oncology; however, comprehensive structural and clinical validation of these targets is crucial to enhance therapeutic efficacy.
Methods: Protein sequences for EGFR, ALK, KRAS, and PD-1 were retrieved from UniProt and modeled using SWISS-MODEL to generate high-confidence 3D structures.
Glycan dysregulation as one of major metabolic subtypes is associated with TERC overexpression and poor outcomes in cervical cancer.
Front Immunol
September 2025
Department of Medicine, Division of Hematology, Bioclinicum and Center for Molecular Medicine, Karolinska Institute and Karolinska University Hospital Solna, Stockholm, Sweden.
Background: Metabolic reprogramming is an important hallmark of cervical cancer (CC), and extensive studies have provided important information for translational and clinical oncology. Here we sought to determine metabolic association with molecular aberrations, telomere maintenance and outcomes in CC.
Methods: RNA sequencing data from TCGA cohort of CC was analyzed for their metabolic gene expression profile and consensus clustering was then performed to classify tumors into different groups/subtypes.
Exploring the biomechanical complexity of glioblastoma spheroids and organoids with co-localized Brillouin and Raman microspectroscopy.
Biochem Biophys Rep
December 2025
Department of Neurosurgery, Faculty of Medicine and University Hospital Carl Gustav Carus, TU Dresden, Dresden, Germany.
Brillouin microscopy allows mechanical investigations of biological materials at the subcellular level and can be integrated with Raman spectroscopy for simultaneous chemical mapping, thus enabling a more comprehensive interpretation of biomechanics. The present study investigates different in vitro glioblastoma models using a combination of Brillouin and Raman microspectroscopy. Spheroids of the U87-MG cell line and two patient-derived cell lines as well as patient-derived organoids were used.
View Article and Find Full Text PDF