Deep Learning in Finance: A Survey of Applications and Techniques

Опубликована: Авг. 20, 2024

Machine learning (ML) has transformed the financial industry by enabling advanced applications such as credit scoring, fraud detection, and market forecasting. At core of this transformation is deep (DL), a subset ML that robust at processing analyzing complex large datasets. This paper provides concise overview key models, including Convolutional Neural Networks (CNNs), Long Short-Term Memory networks (LSTMs), Deep Belief (DBNs), Transformers, Generative Adversarial (GANs), Reinforcement Learning (Deep RL). The study examines their processes, mathematical foundations, practical in finance. It also explores recent advances emerging trends alongside critical challenges data quality, model interpretability, computational complexity, offering insights into future research directions can guide development more explainable models.

Язык: Английский

---

Robust Credit Card Fraud Detection Based on Efficient Kolmogorov-Arnold Network Models

IEEE Access, Год журнала: 2024, Номер 12, С. 157006 - 157020

Опубликована: Янв. 1, 2024

Язык: Английский

---

Credit Card Fraud Detection Using NeuroStack Network and Risk-Based Personalized recommendation with CreditRecHub

Research Square (Research Square), Год журнала: 2024, Номер unknown

Опубликована: Ноя. 12, 2024

The industrial sector suffers annual losses of billions euros due to Credit card fraud, which has increased with the growth online communication channels. Cybercriminals are continuously coming up new ways use network for illegal activities. risk prediction methods frequently encounter issues including inconsistent data distribution and challenging preprocessing. High-precision models often accompanied by low model efficiency. This study presents a comprehensive framework credit fraud detection personalized recommendation systems. A novel NeuroStack Network is proposed assistance acquired from deep learning (CCFD). encapsulates autoencoder, LSTM attention, an ensemble XGBoost SVM. In terms assessment, we propose Risk Scoring Model utilizing Random Forest algorithm combined Dynamic Adjustment through Recurrent Neural Networks (RNNs) integrated Scaled Dot-Product Attention Mechanism, allowing adaptive responsive capabilities.The Personalized Recommendation system referred as CreditRecHub designed using engine risk-based system. Behavioral Profiling process optimized Hybrid Grey Whale Optimization Algorithm (HGWOA) enhance accuracy user behavior analysis. recorded two datasets such 0.98843 0.99976 provided accurate result intrusion detection.

Язык: Английский

---

Innovation in Financial Enterprise Risk Prediction Model

Journal of Organizational and End User Computing, Год журнала: 2024, Номер 36(1), С. 1 - 26

Опубликована: Ноя. 29, 2024

In the context of predicting financial risks for enterprises, traditional methods are inadequate in capturing complex multidimensional data features, resulting suboptimal prediction performance. Although existing deep learning techniques have shown some improvements, they still face challenges processing time series and detecting extended dependencies. To address these issues, this paper proposes an integrated framework utilizing Convolutional Neural Network (CNN), Transformer model, Wavelet Transform (WT). The proposed model leverages CNN to derive local features from data, employs capture long-term dependencies, uses WT multiscale analysis, thereby enhancing accuracy stability predictions. Experimental results demonstrate that CNN-Transformer-WT performs excellently across various datasets, including Kaggle Dataset (Credit Card Fraud Detection Dataset), Bank Marketing Dataset, Yahoo Finance Historical Stock Market Dataset.

Язык: Английский

---