AI-powered microloans are transforming financial inclusion by enabling microenterprises in financially excluded geographies to access critical capital through innovative technologies. This article examines how artificial intelligence addresses traditional microfinance challenges through alternative credit scoring systems that analyze diverse data sources beyond conventional credit histories. By leveraging mobile usage patterns, transaction histories, psychometric assessments, and other digital footprints, AI algorithms create comprehensive risk profiles that extend financial services to previously excluded entrepreneurs. The technology not only improves initial credit assessments but also enhances ongoing risk management through behavioral analytics that predict repayment issues before they materialize. Despite significant technical implementation challenges in connectivity-limited regions, the article explores promising solutions, including edge computing, explainable AI frameworks, adaptive learning systems, and federated learning approaches. Ethical considerations regarding data privacy, algorithmic bias, and interest rate transparency require careful attention to ensure these innovations promote genuine inclusion. The evolution of this field points toward embedded financial services, decentralized finance integration, and collaborative AI models that could further democratize access to capital for marginalized entrepreneurs worldwide.
Decentralized Finance (DeFi) represents a paradigm shift in the financial ecosystem, leveraging blockchain technology to offer innovative, transparent, and permissionless financial services. By eliminating intermediaries, DeFi applications enable direct peer-to-peer transactions and smart contract-driven solutions for lending, borrowing, trading, and asset management. This paper explores the architecture and functionalities of blockchain-based DeFi applications, highlighting their potential to enhance financial inclusivity, reduce transaction costs, and improve system efficiency. Key technical components such as decentralized exchanges (DEXs), liquidity pools, and yield farming are examined, along with the role of governance tokens in community-driven ecosystems. The paper also addresses critical challenges, including scalability, security vulnerabilities, regulatory compliance, and market volatility, which can impact DeFi's adoption and sustainability. Through case studies and performance analyses of leading DeFi platforms, this study provides insights into the transformative potential of blockchain-based DeFi applications in reshaping traditional financial paradigms.
Hong-Sheng Huang, Jason Y. Ho, Hao Chen, Hung–Min Sun
Poorly designed smart contracts are particularly vulnerable, as they may allow attackers to exploit weaknesses and steal the virtual currency they manage. In this study, we train a model using unsupervised learning to identify vulnerabilities in the Solidity source code of Ethereum smart contracts. To address the challenges associated with real-world smart contracts, our training data is derived from actual vulnerability samples obtained from datasets such as SmartBugs Curated and the SolidiFI Benchmark. These datasets enable us to develop a robust unsupervised static analysis method for detecting five specific vulnerabilities: Reentrancy, Access Control, Timestamp Dependency, tx.origin, and Unchecked Low-Level Calls. We employ clustering algorithms to identify outliers, which are subsequently classified as vulnerable smart contracts.
Blockchain and smart contracts have emerged as revolutionary technologies transforming distributed computing. While platform evolution and smart contracts' inherent immutability necessitate migrations both across and within chains, migrating the vast amounts of critical data in these contracts while maintaining data integrity and minimizing operational disruption presents a significant challenge. To address these challenges, we present SmartShift, a framework that enables secure and efficient smart contract migrations through intelligent state partitioning and progressive function activation, preserving operational continuity during transitions. Our comprehensive evaluation demonstrates that SmartShift significantly reduces migration downtime while ensuring robust security, establishing a foundation for efficient and secure smart contract migration systems.
The main purpose of this paper is to compare the forecasting results of time series machine learning models to predict the cryptocurrencies’ future prices for pre-COVID-19, during COVID-19 and post COVID 19 pandemics. Time series data collected from Yahoo Finance was used for the period between January 2017 till February 2024 as test data and the training data to predict 12 months from March 2024 till February 2025. The author undertook three machine learning models: SARIMA, LSTM and FbProphet for the forecasting analysis. LSTM model performs well in predicting the daily price forecasting as compared to SARIMA and Fb prophet models. Bitcoin is predicted to be in the range of $55000 to $65000 by February 2025. Results show a robust trend of volatility during COVID and post COVID periods and pre COVID period was not volatile resulting to no price movements. Based on the forecasting results post-COVID-19 pandemic, the LSTM model outperforms with better predictions than the other models. The findings also revealed that LSTM-RNN model can significantly increase the predictive power in the studies of deep learning models. This paper contributes to the literature on machine learning and forecasting models and the finding provides unique information while modeling the returns. It also insights on what machine learning model is the best to predict movements in the time series data. The results in this paper are expected to enhance our understanding on the role of machine learning models in forecasting future prices of investment instruments in the market, making it valuable for academics, investors, and policymakers alike.
The study examines research on Blockchain technology in the global finance using trends analysis, bibliometric analysis, and literature review using the Elsevier Scopus database from 2016-2023. The findings showed that (Blockchain in Financial Management) BCFin research has generated 185 publications comprising 53.5% articles, 45.4% conference proceedings and 1.1% reviews. The subject area analysis revealed three major publications, groupings spanning Computer Science, Engineering, and Decision Sciences. In contrast, the source titles revealed ACM International Conference Proceeding Series, Sustainability Switzerland, and E3S Web of Conferences as the top mediums of publications for BCF in researchers. Stakeholders analysis showed that the top researchers and affiliations for BCFin are Jon M. Truby and Qatar University (Qatar), with 4 and % publications, respectively. The most productive nation on the topic is China, which is largely ascribed to active funding agencies such as the National Natural Science Foundation (NNSF) of China, which has funded 18 publications. Keywords Co-occurrence Analysis revealed that the top three keywords on BCFin are Blockchain, Finance, and Supply Chain Finance. Cluster analysis revealed three (3) clusters comprising 4-8 keywords, 132 links, and a TLS of 866. Based on the keywords, these clusters could be broadly categorised as the following terms: Integrated Business Solutions (Cluster 1), Digital Commerce Infrastructure (Cluster 2), and Decentralized Financial Network (Cluster 3). The findings indicate that BCFin is an active, multidisciplinary, and impactful research area. BCFin has transformed the global financial industry by overcoming trust issues, enhancing transaction security, and improving communication effectiveness, but it still faces challenges like interoperability, system integration, and sustainability.
Traditional crowdfunding platforms often face challenges like lack of trust, transparency, security, and risks of fraud. To address these limitations, there is a need for a decentralized and secure system. In this paper, we propose a blockchain-based crowdfunding framework aimed to improve trust, security, and efficiency in fundraising for businesses. The framework uses smart contract written in Solidity to automate processes of campaign creation, contribution and fund allocation. The architecture is designed in multiple layers that uses tools like MetaMask for secure user interaction, and Ganache for local testing, back-end layer for API management, and security layer with multi-signature wallets, and smart contract protection to safeguard user funds. We followed a phased approach, starting with front-end design, blockchain integration, and testing before deploying to the Ethereum MainNet. This framework has decentralized fund management and enhanced security measures to address the limitations of traditional crowdfunding systems. It provides a platform where project creator can directly interact with investors. This system has a built-in mechanism for approving funding request through a voting system. This study presents a detailed technical architecture and implementation strategy. It also explores the potential of blockchain technology in strengthening trust, increasing accountability and decentralizing financial system.
Noor Ul Ain Afzal, Muhammad Kamran Abid, Muhammad Fuzail, Naeem Aslam · 5 authors
Ponzi schemes have surfaced on the Ethereum platform as blockchain technology continues to gain traction. Using smart contracts, these schemes, also referred to as smart Ponzi schemes, have caused significant financial losses and adverse effects. Byte code features, op code characteristics, account qualities, and smart contract transaction behavior are the main focus areas for current Ethereum smart Ponzi scheme detection techniques. However, these methods often do not record the behavioral features of the Ponzi scheme, resulting in high false alarm rates and poor identification accuracy. In this study, we provide the source P. Source P is a unique way of knowing intelligent Ponzi schemes on the Ethereum platform, passed by dataflow. Using the intelligent contract's source code as a function eliminates the difficulty of collecting data and extracting functions from available identification methods. In particular, we convert the code into statistical flow diagrams, apply educated models, and use code representations to create classification models for the detection of Ponzi schemes. Experimental results show that SourceP outperforms cutting-edge technology in terms of sustainability and effectiveness, achieving an F1 score of 92.4% and a recall of 90.1% in Ethereum's smart Ponzi schema detection. Ponzi, Blockchain, Source Code, Intelligent Contracts.
S Rohith, V. Sutha, M.Harshitha Reddy, Haider Mohammed Abbas · 6 authors
Competition dictates a fast, transparent, and fraud-proof process, which traditional banks in their mechanisms fall short of among other things due to lengthy paperwork, manual validation, and overreliance on centralized credit bureau scoring. The groundbreaking aspect of blockchain technology lies in decentralizing credit assessment, automation of loan processing through smart contracts, and guaranteeing the transparency of financial transactions. This paper introduces a Blockchain-based Smart Loan Approval System for alleviating the bottlenecks of inefficiencies, security, cost, and accessibility faced due to centralized appraisal and documentation in banking. With the system, the borrower risk is assessed in real-time as financial data at many brokerages are aggregated, the outliers are minimized, and the processing time should be reduced from weeks to minutes. In addition, the Know Your Customer (KYC) and Anti-Money Laundering (AML) verification using crypto ensures that compliance is maintained while preserving the user’s privacy. With this evaluation of key performance metrics, transaction speed, security, and cost efficiency, the proposed framework is compared to conventional lending systems and shows tremendous improvements. Finally, this study points toward how the use of blockchain in banking can assist in bringing down fraud in loans and also bring financial inclusion to all people. In the future, we can integrate artificial intelligence (AI) to perform the dynamic risk assessment, as well as extend it to the decentralized finance (DeFi) applications in traditional banking.
Decentralized finance (DeFi) lending platforms often require over-collateralization, excluding users without substantial crypto holdings. This paper introduces LFG, a novel DeFi protocol that leverages on-chain social profiles and tokenized reputation to assess creditworthiness. By integrating Ethereum smart contracts with Layer-2 solutions (Ethereum, Polygon), decentralized storage (IPFS) and zero-knowledge proofs, LFG enables undercollateralized loans while preserving privacy. We present a technical architecture, analyze security risks, and compare LFGs with traditional models using quantitative metrics. The results show a 40% reduction in collateral requirements for users with high reputation scores on the chain.
In the light of frequent requests from the business sector, blockchain technology and green innovations are integrated into sustainable business models to improve transparency, efficiency, and environment responsibility. This paper presents GreenChain, a blockchain based decentralized framework which helps businesses in attaining sustainability by carbon credit tokenization, peer to peer (P2P) renewable energy trading, and smart green impact analytics powered by artificial intelligence. According to the proposed system, sustainable transactions are accomplished through smart contracts, which guarantee a safe hand and trust reduction of mediators and eliminate the risks of green washing. Incorporating Internet of Things (IoT) based energy monitoring of actual time carbon emissions to be able to earn and trade blockchain verified carbon credits, the framework is integrated. Additionally, it allows tokenized investments to fund green projects in a decentralized finance (DeFi) mechanism. The feasibility of low cost, high security transactions is also discussed in terms of analysis of performance, which render it into a viable alternative of conventional means of sustainability tracking mechanism. This paper discusses its research on the use of blockchain towards carbon footprint, energy efficiency and circular economy. The results suggest that both the GreenChain model strengthens accountability and facilitates ESG compliance, which avers the industry’s transition towards a sustainable future. Eutopia will concentrate on making adoption of the ADU widely scalable, complying to regulatory standards, and introducing it in smart cities and industrial ecosystems.
E.Sri Durgadevi, V. Sutha, Hassan M. Al‐Jawahry, Polepaka Sanjeeva · 6 authors
The paper focuses on incorporating cryptocurrencies into corporate finance by creating an innovative, AI-powered decentralized finance (DeFi), that could possibly be used to invest. For decades, corporates funds has been mostly funded through assets like stocks and bonds which have now been joined by another asset, namely cryptocurrencies. Nevertheless, legal uncertainty, high volatility, and lack of institutional trust have so far prevented their wide spread adoption. This paper introduces a solution to addressing these challenges that takes a risk management approach with AI involved, blocks out the asset tokenization and decentralized autonomous organizations (DAO). The proposed framework looks for the decrease of having more stable and more profitable investment decisions through the use of AI models for market analysis and risk assessment. Investment pool token or smart contract tokens allow investing in various assets including stocks, bonds, corporates, art, real estate, crypto, idle fiat, and more — as well as the governance token, which helps with scaling the mean world token. Interoperability of cross chain, provides access to all of the blockchain ecosystem in a simple, transparent manner. And this is done through decentralised governance via DAOs. This is a novel way to cut risks, transparency and unlock new investment opportunities for companies, who would use cryptocurrencies as a speculative asset not any more, but a part of a diversified financial strategy. Introducing these technologies allows corporations to invest in their portfolios and achieve better liquidity, stability, and long run sustainable investment.
T Rajasrutheeswaran, V. Sutha, Zaid Alsalami, Patolla Sruthi · 6 authors
However, users perceive the blockchain crowdfunding platforms as promising terms of financial tool for business startup; meanwhile, existing platforms fail to provide transparent operations or demonstrable impact measurement or provide an incentive to long term investors. Using smart contracts with linked sustainability and decentralized administrative controls, GreenFundChain provides a new blockchain platform that is able to meet three main features: tokenized investments allowing for social and environmental benefits to be measured, and supported by tokenized investments. The platform authorizes funding when the Environmental Social Governance (ESG) performance targets are completed after sustainability audits are executed by AI systems combined with Internet of Things monitoring. The responsibility of Decentralized Autonomous Organization responsible for operating through the community-based governance decision includes the fall on fund distribution along with project selection. As sustainability performance increases, the value of GreenImpact Tokens (GITs) increases and investors are more inclined attracted to projects through extended participation. Carbon credit functionality is added to the new venture to create eco-footprint marketables combined with sustainable micro-band investments. Implementation of prototyping of the platform, guarantees transaction security and smart contract efficiency and impact verifiability accuracy based on which it becomes a trust-building platform and prevents fraud from crowdfunding. It has single and significantly better protection for investors, and an equally good transparency as well as sustainability verification compared to other solutions. Through this research project, we make a contribution to the development of blockchain financial ecosystem by creating a link aimed to support the crawling crowdfunding campaigns.
The emergence of the Metaverse as a decentralized digital ecosystem has transformed traditional contract enforcement by introducing smart contracts, self-executing agreements embedded in blockchain systems. This study conducts a comparative legal analysis of the regulatory frameworks governing smart contracts within Metaverse operations in Nigeria and Uganda. Employing a doctrinal legal method, the research critically examines primary legal sources such as statutory laws and case law, alongside scholarly literature, to assess legal recognition, enforceability, and institutional preparedness. The study reveals a significant regulatory gap in Nigeria, where the absence of a comprehensive legal framework creates uncertainty in the enforceability of smart contracts, despite growing blockchain policy initiatives. In contrast, Uganda has established more definitive legal provisions, particularly through its Electronic Transactions and Signature Acts, which explicitly validate digital contracts. The novelty of this study lies in its regional comparative focus on emerging economies and its analysis of how traditional contract principles interact with decentralized digital platforms. The urgency of this inquiry is underscored by the rapid digitalization of commerce, which necessitates timely legal adaptation to prevent regulatory obsolescence and safeguard stakeholders. This research contributes to the discourse on digital governance by proposing a legal reform agenda for Nigeria, advocating for the adoption of a smart contract-enabling framework modeled after Uganda’s approach. Ultimately, it calls for regional and international harmonization to ensure legal certainty, consumer protection, and dispute resolution within Metaverse-driven economies.
Distributed Ledger Technologies (DLTs) and smart contracts are revolutionizing industries by enabling transparent, decentralized, and automated transactions. However, the security of smart contracts remains a significant concern, as vulnerabilities can undermine the reliability of such systems and lead to substantial financial losses. Despite the critical importance of ensuring their integrity, there is a notable lack of automated frameworks to comprehensively assess smart contracts' security throughout their lifecycle, leaving them susceptible to various threats. This position paper proposes a framework to enhance smart contract security auditing, i.e., to efficiently and effectively support smart contract code analysis and testing and identify critical vulnerabilities. The framework encompasses several key components: identification of a target security profile, prioritization of potential vulnerabilities, systematic testing planning and execution, and a robust auditing and certification process. By establishing a structured approach to testing, we aim to enhance the security and reliability of smart contracts. In addition, we analyze the open challenges that must be addressed to build this framework effectively.
Anuj J. Ghom, Atharv N. Phuse, Harish S. Chopade, Mahesh A. Ghongade · 5 authors
Crowdfunding has emerged as a vital mechanism for raising funds, enabling startups, social causes, and creative projects to receive financial support from a broad audience.However, traditional crowdfunding platforms face challenges such as high transaction fees, lack of transparency, centralized control, and risks of fraud or fund mismanagement.To address these issues, we propose a Blockchain-Based Decentralized Crowdfunding Platform that leverages blockchain technology and smart contracts to enhance security, transparency, and trust in fundraising.By eliminating intermediaries, the system facilitates direct peer-to-peer transactions, ensuring immutability and automated fund distribution based on predefined conditions.This implementation utilizes the Ethereum blockchain to create an environment where fundraisers and backers can interact securely.The paper details the system architecture, smart contract design, security considerations, and a comparative analysis with traditional crowdfunding models.The results demonstrate improved transparency, reduced operational costs, and enhanced trust in the crowdfunding ecosystem.
Edgar Roberto Dulce Villarreal, Giovanni Hernández, Jesús Insuasti, Julio Ariel Hurtado Alegría · 5 authors
The exchange of medical information significantly benefits people's quality of life, improving their care and treatment. The interoperability of the entire healthcare ecosystem is a constant challenge. Blockchain technology is an alternative to find a balance in the healthcare ecosystem. Smart contracts (SC) are decentralized and self-executing programs that allow the automation of agreements without intermediaries to improve operational efficiency. However, the constant development of new Blockchain technologies and programming languages for smart contracts is a growing problem. This work presents the validation by expert judgment of the MUISCA (Mechanism for UnIversal SmartContrAct) tool, which uses Model Driven Engineering (MDE). MUISCA uses transformations of models and models to text to generate smart contracts in healthcare environments and specific to Blockchain platforms. The validation is conducted by smart contracts development experts, who show positivity in the perceived usefulness.
Purpose This paper aims to elucidate the factors influencing individuals’ cryptocurrency adoption within the distinctive socio-economic context of a developing country. It argues that encouraging financial innovation and understanding cryptocurrency adoption is crucial for businesses, regulators and researchers. Design/methodology/approach It investigates factors affecting cryptocurrency adoption by integrating the Theory of Planned Behavior (TPB), Innovation Diffusion Theory (IDT) and the Trust-Risk Framework. It employed Structural Equation Modeling (SEM) on data collected from 370 respondents. Findings Results indicate that attitude significantly influences intention to use cryptocurrency, with trust being the most influential factor shaping attitude. Relative advantage and compatibility positively influence attitudes toward cryptocurrency, whereas complexity has a negative effect. Observability was not a significant predictor of attitude. Interestingly, perceived risk positively affects trust in cryptocurrencies. Research limitations/implications Findings reflecting the context of Türkiye may not be generalizable to countries with different cultural or legal contexts. The high education level of participants could introduce bias due to their likely higher technology literacy. Practical implications The findings inform various stakeholders about cryptocurrency adoption in emerging countries. Social implications Understanding dynamics influencing attitudes and intentions contributes to socio-economic discussions on integrating cryptocurrencies into mainstream financial systems. Originality/value This research contributes to theory and practice by providing empirical insights into the dynamics of cryptocurrency adoption in emerging countries. By synthesizing established theories, this study advances understanding and enriches comprehension of the factors influencing adoption in emerging economies.
Purpose This study investigates herd behavior in the Fan Tokens market, comparing it with the non-fungible tokens (NFTs) and traditional cryptocurrency markets. Design/methodology/approach This study investigates herding behavior by examining the relationship between the cross-sectional dispersion of asset returns and overall market returns, utilizing five distinct model specifications. To enhance the robustness of the findings, the regressions are re-estimated using the GARCH model, ensuring more reliable parameter estimates and capturing the impact of volatility on herding behavior. Findings The analysis reveals strong evidence of herd behavior in the Fan Token market, particularly during bearish conditions, heightened volatility, and low trading volume. Positive news was found to amplify volatility more than negative news. In contrast, no statistically significant herd behavior was identified in the NFT and traditional cryptocurrency markets, where investors showed a more cautious response to market conditions. Practical implications Understanding the unique dynamics of Fan Tokens can help investors, regulators, and market participants make informed decisions and develop strategies to mitigate risks associated with herd behavior and volatility in this rapidly evolving market. Originality/value This study highlights the unique characteristics of Fan Tokens, emphasizing their strong ties to fan sentiment and sports outcomes, as well as the role of uninformed investors in shaping market dynamics. The findings contribute to the literature on digital asset markets and investor psychology, offering novel insights into this emerging asset class.
The rise of digital finance has led to a surge in fraudulent activities, particularly in credit card transactions and cryptocurrency ecosystems. With financial crimes becoming more sophisticated, traditional fraud detection methods often fail to identify complex fraudulent patterns. This research explores the application of machine learning (ML) and artificial intelligence (AI) techniques to enhance the security of digital finance by detecting fraudulent activities in credit card transactions and cryptocurrency wallets within the USA. The study utilizes large-scale transaction datasets containing key financial indicators such as transaction frequency, spending patterns, anomaly scores, and network behaviors. To develop an AI-driven fraud detection framework, we implement and compare six machine learning models: XGBoost, RLightGBM, Decision Trees, K-Nearest Neighbors (KNN), Convolutional Neural Networks (CNNs), and Autoencoders. The models are trained on both structured financial data (e.g., credit card transaction logs) and unstructured blockchain transaction records (e.g., Bitcoin wallet addresses and transaction flows). To address data imbalance, the study applies the Synthetic Minority Over-sampling Technique (SMOTE), ensuring fair representation of fraudulent transactions. Model performance is evaluated using Precision, Recall, F1-score, and ROC-AUC metrics to determine the most effective fraud detection approach. Additionally, the research emphasizes data privacy and security, incorporating anonymization techniques and regulatory compliance measures to safeguard sensitive financial information. This study contributes to the ongoing fight against financial fraud by demonstrating how AI-based solutions can enhance the security and resilience of digital finance systems in the USA.
Sadaf Azimi, Ali Golzari, Naghmeh Ivaki, Nuno Laranjeiro
Abstract Smart contracts have accelerated the adoption of blockchain technology across various domains by enabling coded agreements between transaction participants. However, increased software defects and vulnerabilities in smart contracts, driven by developer inexperience with languages like Solidity and a lack of effective detection tools, pose significant risks. Given the high value of assets managed on blockchain (e.g., cryptocurrencies), these vulnerabilities can lead to severe consequences. Researchers and practitioners have proposed numerous smart contract design patterns to mitigate certain faults or vulnerabilities. Despite these efforts, it remains unclear which types of defects these patterns target and how effectively they address the wide range of existing smart contract security vulnerabilities. In this paper, we review the state of the art in smart contract design patterns, categorizing them and analyzing their effectiveness in mitigating known security vulnerabilities. Our findings reveal that only five patterns directly aim to prevent security vulnerabilities, collectively addressing just 6 out of 94 security issues identified by OpenSCV (a state-of-the-art vulnerability taxonomy), highlighting the need for further research on smart contract security design patterns.
This paper investigates the impact of cross-chain deployment on the market performance of decentralized applications (Dapps) within the evolving multichain Web3 ecosystem. While cross-chain Dapps benefit from broader user reach, improved scalability, and enhanced resilience, they also face significant challenges, including technical complexities, security risks, and fragmented liquidity. This paper analyses how Dapps' transaction distribution across multiple blockchains influences their market performance. Preliminary findings reveal that Dapps operating on multiple chains tend to underperform in terms of market capitalization, token price, and transaction volume compared to those concentrated on a single or few chains. These results highlight critical concerns about the effectiveness of cross-chain strategies.
José Juan de León, Cenchuan Zhang, Christos - Spyridon Koulouris, Francesca Medda · 5 authors
The growing interest in decentralized finance (DeFi), driven by advancements in blockchain technologies such as Ethereum, highlights the crucial role of smart contracts. However, the inherent openness of blockchains creates an extensive attack surface, exposing participants’ funds to undetected security flaws. In this work we investigated the use of deep reinforcement learning techniques, specifically Deep Q-Network (DQN) and Proximal Policy Optimization (PPO), for detecting and classifying vulnerabilities in smart contracts. This approach utilizes control flow graphs (CFGs) generated through EtherSolve to capture the semantic features of contract bytecode, enabling the reinforcement learning models to recognize patterns and make more accurate predictions. Experimental results from extensive public datasets of smart contracts revealed that the PPO model performs better than DQN and demonstrates effectiveness in identifying unchecked-call vulnerability. The PPO model exhibits more stable and consistent learning patterns and achieves higher overall rewards. This research introduces a machine learning method for enhancing smart contract security, reducing financial risks for users, and contributing to future developments in reinforcement learning applications.