Fintech

Financial Text Classification Based On rLoRA Finetuning On Qwen3-8B model ArXiv ID: 2512.00630 “View on arXiv” Authors: Zhiming Lian Abstract Financial text classification has increasingly become an important aspect in quantitative trading systems and related tasks, such as financial sentiment analysis and the classification of financial news. In this paper, we assess the performance of the large language model Qwen3-8B on both tasks. Qwen3-8B is a state-of-the-art model that exhibits strong instruction-following and multilingual capabilities, and is distinct from standard models, primarily because it is specifically optimized for efficient fine tuning and high performance on reasoning-based benchmarks, making it suitable for financial applications. To adapt this model, we apply Noisy Embedding Instruction Finetuning and based on our previous work, this method increases robustness by injecting controlled noise into the embedding layers during supervised adaptation. We improve efficiency further with Rank-stabilized Low-Rank Adaptation low-rank optimization approach, and FlashAttention, which allow for faster training with lower GPU memory. For both tasks, we benchmark Qwen3-8B against standard classical transformer models, such as T5, BERT, and RoBERTa, and large models at scale, such as LLaMA1-7B, LLaMA2-7B, and Baichuan2-7B. The findings reveal that Qwen3-8B consistently surpasses these baselines by obtaining better classification accuracy and needing fewer training epochs. The synergy of instruction-based fine-tuning and memory-efficient optimization methods suggests Qwen3-8B can potentially serve as a scalable, economical option for real-time financial NLP applications. Qwen3-8B provides a very promising base for advancing dynamic quantitative trading systems in the future. ...

Responsible LLM Deployment for High-Stake Decisions by Decentralized Technologies and Human-AI Interactions ArXiv ID: 2512.04108 “View on arXiv” Authors: Swati Sachan, Theo Miller, Mai Phuong Nguyen Abstract High-stakes decision domains are increasingly exploring the potential of Large Language Models (LLMs) for complex decision-making tasks. However, LLM deployment in real-world settings presents challenges in data security, evaluation of its capabilities outside controlled environments, and accountability attribution in the event of adversarial decisions. This paper proposes a framework for responsible deployment of LLM-based decision-support systems through active human involvement. It integrates interactive collaboration between human experts and developers through multiple iterations at the pre-deployment stage to assess the uncertain samples and judge the stability of the explanation provided by post-hoc XAI techniques. Local LLM deployment within organizations and decentralized technologies, such as Blockchain and IPFS, are proposed to create immutable records of LLM activities for automated auditing to enhance security and trace back accountability. It was tested on Bert-large-uncased, Mistral, and LLaMA 2 and 3 models to assess the capability to support responsible financial decisions on business lending. ...

Temporal Graph Networks for Graph Anomaly Detection in Financial Networks ArXiv ID: 2404.00060 “View on arXiv” Authors: Unknown Abstract This paper explores the utilization of Temporal Graph Networks (TGN) for financial anomaly detection, a pressing need in the era of fintech and digitized financial transactions. We present a comprehensive framework that leverages TGN, capable of capturing dynamic changes in edges within financial networks, for fraud detection. Our study compares TGN’s performance against static Graph Neural Network (GNN) baselines, as well as cutting-edge hypergraph neural network baselines using DGraph dataset for a realistic financial context. Our results demonstrate that TGN significantly outperforms other models in terms of AUC metrics. This superior performance underlines TGN’s potential as an effective tool for detecting financial fraud, showcasing its ability to adapt to the dynamic and complex nature of modern financial systems. We also experimented with various graph embedding modules within the TGN framework and compared the effectiveness of each module. In conclusion, we demonstrated that, even with variations within TGN, it is possible to achieve good performance in the anomaly detection task. ...

Empowering Credit Scoring Systems with Quantum-Enhanced Machine Learning ArXiv ID: 2404.00015 “View on arXiv” Authors: Unknown Abstract Quantum Kernels are projected to provide early-stage usefulness for quantum machine learning. However, highly sophisticated classical models are hard to surpass without losing interpretability, particularly when vast datasets can be exploited. Nonetheless, classical models struggle once data is scarce and skewed. Quantum feature spaces are projected to find better links between data features and the target class to be predicted even in such challenging scenarios and most importantly, enhanced generalization capabilities. In this work, we propose a novel approach called Systemic Quantum Score (SQS) and provide preliminary results indicating potential advantage over purely classical models in a production grade use case for the Finance sector. SQS shows in our specific study an increased capacity to extract patterns out of fewer data points as well as improved performance over data-hungry algorithms such as XGBoost, providing advantage in a competitive market as it is the FinTech and Neobank regime. ...

On Finding Bi-objective Pareto-optimal Fraud Prevention Rule Sets for Fintech Applications ArXiv ID: 2311.00964 “View on arXiv” Authors: Unknown Abstract Rules are widely used in Fintech institutions to make fraud prevention decisions, since rules are highly interpretable thanks to their intuitive if-then structure. In practice, a two-stage framework of fraud prevention decision rule set mining is usually employed in large Fintech institutions; Stage 1 generates a potentially large pool of rules and Stage 2 aims to produce a refined rule subset according to some criteria (typically based on precision and recall). This paper focuses on improving the flexibility and efficacy of this two-stage framework, and is concerned with finding high-quality rule subsets in a bi-objective space (such as precision and recall). To this end, we first introduce a novel algorithm called SpectralRules that directly generates a compact pool of rules in Stage 1 with high diversity. We empirically find such diversity improves the quality of the final rule subset. In addition, we introduce an intermediate stage between Stage 1 and 2 that adopts the concept of Pareto optimality and aims to find a set of non-dominated rule subsets, which constitutes a Pareto front. This intermediate stage greatly simplifies the selection criteria and increases the flexibility of Stage 2. For this intermediate stage, we propose a heuristic-based framework called PORS and we identify that the core of PORS is the problem of solution selection on the front (SSF). We provide a systematic categorization of the SSF problem and a thorough empirical evaluation of various SSF methods on both public and proprietary datasets. On two real application scenarios within Alipay, we demonstrate the advantages of our proposed methodology over existing work. ...

The Rise and Fall of Cryptocurrencies: Defining the Economic and Social Values of Blockchain Technologies, assessing the Opportunities, and defining the Financial and Cybersecurity Risks of the Metaverse ArXiv ID: 2309.12322 “View on arXiv” Authors: Unknown Abstract This paper contextualises the common queries of “why is crypto crashing?” and “why is crypto down?”, the research transcends beyond the frequent market fluctuations to unravel how cryptocurrencies fundamentally work and the step-by-step process on how to create a cryptocurrency. The study examines blockchain technologies and their pivotal role in the evolving Metaverse, shedding light on topics such as how to invest in cryptocurrency, the mechanics behind crypto mining, and strategies to effectively buy and trade cryptocurrencies. Through an interdisciplinary approach, the research transitions from the fundamental principles of fintech investment strategies to the overarching implications of blockchain within the Metaverse. Alongside exploring machine learning potentials in financial sectors and risk assessment methodologies, the study critically assesses whether developed or developing nations are poised to reap greater benefits from these technologies. Moreover, it probes into both enduring and dubious crypto projects, drawing a distinct line between genuine blockchain applications and Ponzi-like schemes. The conclusion resolutely affirms the continuing dominance of blockchain technologies, underlined by a profound exploration of their intrinsic value and a reflective commentary by the author on the potential risks confronting individual investors. ...

Deep Learning and Financial Stability ArXiv ID: ssrn-3723132 “View on arXiv” Authors: Unknown Abstract The financial sector is entering a new era of rapidly advancing data analytics as deep learning models are adopted into its technology stack. A subset of Artifi Keywords: Deep Learning, Data Analytics, Fintech, Natural Language Processing (NLP), Financial Modeling, Multi-Asset Complexity vs Empirical Score Math Complexity: 2.5/10 Empirical Rigor: 1.0/10 Quadrant: Philosophers Why: The paper is a conceptual policy analysis that identifies theoretical transmission pathways (e.g., data aggregation, model design) for systemic risk without presenting mathematical models, statistical metrics, or backtesting results. It focuses on qualitative governance frameworks rather than quantitative implementation. flowchart TD A["Research Goal: Deep Learning in Financial Stability"] --> B["Data Inputs & Methodology"] B --> C["Computational Processes"] C --> D["Key Findings & Outcomes"] B --> B1["Multi-Asset Data"] B --> B2["NLP on Financial Text"] B --> B3["Alternative Data Sources"] C --> C1["Deep Learning Models"] C --> C2["Financial Stability Metrics"] C --> C3["Risk Assessment Algorithms"] D --> D1["Enhanced Risk Prediction"] D --> D2["Systemic Stability Insights"] D --> D3["Fintech Innovation Pathways"] style A fill:#e1f5fe style D fill:#e8f5e8

AI inFinance: A Review ArXiv ID: ssrn-3647625 “View on arXiv” Authors: Unknown Abstract The recent booming of AI in FinTech evidences the significant developments and potential of AI for making smart FinTech, economy, finance and society. AI-empowe Keywords: Artificial Intelligence (AI), FinTech, Machine Learning in Finance, Smart Economy, Multi-Asset / Technology Complexity vs Empirical Score Math Complexity: 1.5/10 Empirical Rigor: 1.0/10 Quadrant: Philosophers Why: The excerpt is a literature review summarizing broad trends in AI and finance using high-level concepts and Google search data, with no advanced mathematical formulas or empirical backtesting details presented. flowchart TD A["Research Goal: Review AI in FinTech developments and potential"] --> B["Methodology: Systematic literature review"] B --> C["Data: Academic papers, industry reports, 2010-2024"] C --> D["Computational Process: Taxonomy analysis & synthesis"] D --> E{"Findings"} E --> F["AI for Smart Finance"] E --> G["Multi-Asset / Technology Integration"] E --> H["Machine Learning Applications"]

A Survey of Fintech Research and Policy Discussion ArXiv ID: ssrn-3622468 “View on arXiv” Authors: Unknown Abstract The intersection of finance and technology, known as fintech, has resulted in the dramatic growth of innovations and has changed the entire financial landscape. Keywords: Fintech, Financial Technology, Digital Innovation, Financial Landscape, Technology in Finance, Financial Technology Complexity vs Empirical Score Math Complexity: 2.0/10 Empirical Rigor: 2.0/10 Quadrant: Philosophers Why: The paper is a survey and policy discussion, which focuses on broad themes and high-level analysis rather than specific mathematical derivations or empirical backtesting data. flowchart TD A["Research Goal: Understand fintech's impact on the financial landscape"] --> B["Methodology: Literature Review & Data Synthesis"] B --> C["Data/Inputs: Academic Papers, Policy Reports, Industry Trends"] C --> D["Computational Process: Thematic Analysis & Trend Mapping"] D --> E["Key Findings: Innovation Acceleration, Regulatory Challenges, & Market Transformation"]

DecentralizedFinance(DeFi) ArXiv ID: ssrn-3539194 “View on arXiv” Authors: Unknown Abstract DeFi (‘decentralized finance’) has joined FinTech (‘financial technology’), RegTech (‘regulatory technology’), cryptocurrencies, and digital assets as one of th Keywords: Decentralized Finance (DeFi), Fintech, Cryptocurrency, Blockchain, Digital Assets, Crypto / Digital Assets Complexity vs Empirical Score Math Complexity: 1.0/10 Empirical Rigor: 1.0/10 Quadrant: Philosophers Why: The paper is a legal and policy analysis discussing the regulatory implications of decentralized finance, with no mathematical formulas, code, or empirical backtesting presented in the excerpt. flowchart TD A["Research Goal: Impact of DeFi<br>on Traditional Finance"] --> B["Key Methodology: Literature Review &<br>Blockchain Data Analysis"] B --> C{"Data/Inputs"} C --> D["Smart Contract Logs<br>& Transaction Data"] C --> E["Academic Papers &<br>Market Reports"] D & E --> F["Computational Processes"] F --> G["Statistical Analysis of<br>Yield Rates & Liquidity"] F --> H["NLP for Sentiment<br>& Risk Assessment"] G & H --> I["Key Findings: High Returns,<br>Systemic Risks, &<br>Regulatory Challenges"]