[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"hackathon-/hackathons/fintech-hackathon-2024":3,"hackathon-teams-fintech-hackathon-2024":107},{"id":4,"title":5,"bannerImage":6,"body":7,"date":92,"description":93,"endDate":94,"extension":95,"featured":96,"location":97,"meta":98,"navigation":99,"path":100,"seo":101,"stem":102,"theme":103,"totalParticipants":104,"totalTeams":105,"__hash__":106},"hackathons/hackathons/fintech-hackathon-2024.md","FinTech Disruption Hackathon 2024",null,{"type":8,"value":9,"toc":84},"minimark",[10,15,19,23,26,43,47,50,77,81],[11,12,14],"h2",{"id":13},"event-overview","Event Overview",[16,17,18],"p",{},"The FinTech Disruption Hackathon 2024 gathered 72 participants in London to reimagine financial services through AI. Sponsored by three leading European banks and two fintech scale-ups, this event focused exclusively on the unique challenges and regulatory constraints of the financial industry.",[11,20,22],{"id":21},"challenge-tracks","Challenge Tracks",[16,24,25],{},"Teams selected from two core tracks:",[27,28,29,37],"ul",{},[30,31,32,36],"li",{},[33,34,35],"strong",{},"Payments & Fraud"," — Build intelligent systems for real-time fraud detection, payment optimization, or cross-border transaction efficiency",[30,38,39,42],{},[33,40,41],{},"Risk & Compliance"," — Create AI tools that streamline regulatory reporting, automate KYC/AML processes, or improve credit risk modelling",[11,44,46],{"id":45},"judging-criteria","Judging Criteria",[16,48,49],{},"A panel of industry executives and technical leaders evaluated each solution:",[51,52,53,59,65,71],"ol",{},[30,54,55,58],{},[33,56,57],{},"Regulatory Awareness (25%)"," — Understanding of compliance constraints and data privacy",[30,60,61,64],{},[33,62,63],{},"Technical Sophistication (25%)"," — Model quality, system architecture, and code maturity",[30,66,67,70],{},[33,68,69],{},"Customer Impact (25%)"," — Clear benefits for end users or operational teams",[30,72,73,76],{},[33,74,75],{},"Scalability (25%)"," — Ability to handle production volumes and integrate with existing infrastructure",[11,78,80],{"id":79},"results","Results",[16,82,83],{},"The event produced three solutions that entered pilot programmes with sponsoring organizations within 90 days. The winning team's fraud detection prototype reduced false positive rates by 40% on the provided test dataset.",{"title":85,"searchDepth":86,"depth":86,"links":87},"",2,[88,89,90,91],{"id":13,"depth":86,"text":14},{"id":21,"depth":86,"text":22},{"id":45,"depth":86,"text":46},{"id":79,"depth":86,"text":80},"2024-06-07","A focused hackathon for financial services innovation, where teams built AI-driven solutions for payments, risk management, and regulatory compliance. Sponsored by leading European banks and fintech firms.","2024-06-09","md",false,"London, United Kingdom",{},true,"/hackathons/fintech-hackathon-2024",{"title":5,"description":93},"hackathons/fintech-hackathon-2024","AI in Financial Services",72,18,"9ebfECG_UIIX-5mYDVlGCtKmIU2C_ERijewTOXQ1tgY",[108,207,282],{"id":109,"title":110,"body":111,"demoUrl":142,"description":85,"extension":95,"hackathonSlug":143,"members":144,"meta":191,"navigation":99,"path":192,"placement":193,"projectDescription":194,"projectName":195,"repoUrl":196,"seo":197,"stem":198,"technologies":199,"__hash__":206},"hackathonTeams/hackathons/fintech-hackathon-2024/teams/team-payflow.md","Team PayFlow",{"type":8,"value":112,"toc":135},[113,117,120,125,128,132],[11,114,116],{"id":115},"project-details","Project Details",[16,118,119],{},"FraudShield AI reimagines payment fraud detection by moving beyond transaction-level analysis to network-level pattern recognition.",[121,122,124],"h3",{"id":123},"key-innovation","Key Innovation",[16,126,127],{},"The team built a graph neural network that models the entire payment network, where accounts are nodes and transactions are edges. By analysing the topology and temporal dynamics of the network, FraudShield identifies fraud rings and synthetic identity patterns that rule-based systems cannot detect.",[121,129,131],{"id":130},"demo-highlights","Demo Highlights",[16,133,134],{},"The live demonstration processed 1 million simulated transactions in real-time, correctly flagging 94% of fraudulent transactions while reducing false positives by 40%.",{"title":85,"searchDepth":86,"depth":86,"links":136},[137],{"id":115,"depth":86,"text":116,"children":138},[139,141],{"id":123,"depth":140,"text":124},3,{"id":130,"depth":140,"text":131},"https://fraudshield-demo.example.com","fintech-hackathon-2024",[145,162,171,184],{"name":146,"role":147,"bio":148,"links":149},"Anna Bergström","Team Lead & ML Engineer","ML engineer with 7 years of experience in fraud detection and anomaly detection systems.",[150,154,158],{"platform":151,"url":152,"label":153},"linkedin","https://linkedin.com/in/anna-bergstrom","LinkedIn",{"platform":155,"url":156,"label":157},"github","https://github.com/abergstrom","GitHub",{"platform":159,"url":160,"label":161},"twitter","https://twitter.com/anna_ml","Twitter",{"name":163,"role":164,"bio":165,"links":166},"Daniel Okonkwo","Data Engineer","Data engineer specialising in real-time streaming architectures and graph databases.",[167,169],{"platform":155,"url":168,"label":157},"https://github.com/dokonkwo",{"platform":151,"url":170,"label":153},"https://linkedin.com/in/daniel-okonkwo",{"name":172,"role":173,"bio":174,"links":175},"Lisa Zhang","Frontend Developer","Frontend developer focused on data visualisation and real-time monitoring dashboards.",[176,178,180],{"platform":155,"url":177,"label":157},"https://github.com/lisazhang",{"platform":151,"url":179,"label":153},"https://linkedin.com/in/lisa-zhang-dev",{"platform":181,"url":182,"label":183},"website","https://lisazhang.io","Portfolio",{"name":185,"role":186,"bio":187,"links":188},"Henrik Larsen","Domain Expert & Business Analyst","Former banking compliance officer turned fintech consultant with deep payments domain expertise.",[189],{"platform":151,"url":190,"label":153},"https://linkedin.com/in/henrik-larsen-fintech",{},"/hackathons/fintech-hackathon-2024/teams/team-payflow","1st","A real-time fraud detection system using graph neural networks to identify suspicious transaction patterns across payment networks. FraudShield reduced false positive rates by 40% compared to the baseline rule-based system.","FraudShield AI","https://github.com/team-payflow/fraudshield",{"title":110,"description":85},"hackathons/fintech-hackathon-2024/teams/team-payflow",[200,201,202,203,204,205],"Python","PyTorch Geometric","Apache Flink","Neo4j","React","D3.js","_Sn0Umija9zytEFlzwHPUnAo9wOVhxmE1uU5KYVfcuI",{"id":208,"title":209,"body":210,"demoUrl":233,"description":85,"extension":95,"hackathonSlug":143,"members":234,"meta":267,"navigation":99,"path":268,"placement":269,"projectDescription":270,"projectName":271,"repoUrl":272,"seo":273,"stem":274,"technologies":275,"__hash__":281},"hackathonTeams/hackathons/fintech-hackathon-2024/teams/team-riskguard.md","Team RiskGuard",{"type":8,"value":211,"toc":227},[212,214,217,219,222,224],[11,213,116],{"id":115},[16,215,216],{},"RegLens tackles the challenge of keeping up with regulatory changes across multiple jurisdictions.",[121,218,124],{"id":123},[16,220,221],{},"The team built a specialised NLP pipeline that extracts structured requirements from regulatory documents and maps them to an organisation's internal control framework. When a new regulation is published, RegLens automatically identifies which controls need updating and generates draft remediation plans.",[121,223,131],{"id":130},[16,225,226],{},"The team showed RegLens processing a newly published MiFID II amendment and identifying 7 internal controls that required updates within seconds — a task that would typically take a compliance team 2-3 days.",{"title":85,"searchDepth":86,"depth":86,"links":228},[229],{"id":115,"depth":86,"text":116,"children":230},[231,232],{"id":123,"depth":140,"text":124},{"id":130,"depth":140,"text":131},"https://reglens-demo.example.com",[235,244,257],{"name":236,"role":237,"bio":238,"links":239},"Fatima Al-Rashid","Team Lead & NLP Engineer","NLP engineer with expertise in legal document analysis and financial regulation extraction.",[240,242],{"platform":151,"url":241,"label":153},"https://linkedin.com/in/fatima-alrashid",{"platform":155,"url":243,"label":157},"https://github.com/falrashid",{"name":245,"role":246,"bio":247,"links":248},"Christopher Wright","Backend Developer","Backend developer with experience building scalable document processing systems.",[249,251,253],{"platform":155,"url":250,"label":157},"https://github.com/cwright",{"platform":151,"url":252,"label":153},"https://linkedin.com/in/christopher-wright-dev",{"platform":254,"url":255,"label":256},"gitlab","https://gitlab.com/cwright","GitLab",{"name":258,"role":259,"bio":260,"links":261},"Yuki Tanaka","Data Scientist","Data scientist with a background in financial risk modelling and regulatory technology.",[262,264],{"platform":151,"url":263,"label":153},"https://linkedin.com/in/yuki-tanaka",{"platform":181,"url":265,"label":266},"https://yukitanaka.com","Blog",{},"/hackathons/fintech-hackathon-2024/teams/team-riskguard","2nd","An AI-powered regulatory change management platform that monitors global financial regulations, extracts requirements, and maps them to internal controls. RegLens demonstrated automated compliance gap analysis across 3 jurisdictions.","RegLens","https://github.com/team-riskguard/reglens",{"title":209,"description":85},"hackathons/fintech-hackathon-2024/teams/team-riskguard",[200,276,277,278,279,280],"spaCy","GPT-4","FastAPI","Vue.js","Elasticsearch","x4SvQ6RIw3hi2IkafKmfW5QKOqYIw2qncoXkEzMzodg",{"id":283,"title":284,"body":285,"demoUrl":308,"description":85,"extension":95,"hackathonSlug":143,"members":309,"meta":341,"navigation":99,"path":342,"placement":343,"projectDescription":344,"projectName":345,"repoUrl":346,"seo":347,"stem":348,"technologies":349,"__hash__":353},"hackathonTeams/hackathons/fintech-hackathon-2024/teams/team-smartledger.md","Team SmartLedger",{"type":8,"value":286,"toc":302},[287,289,292,294,297,299],[11,288,116],{"id":115},[16,290,291],{},"CreditSense challenges the status quo of credit scoring by combining traditional financial indicators with alternative data sources.",[121,293,124],{"id":123},[16,295,296],{},"The team implemented a fairness-constrained gradient boosting model that achieves better predictive performance than traditional scorecards while provably reducing demographic bias. Every scoring decision comes with a SHAP-based explanation that satisfies regulatory requirements.",[121,298,131],{"id":130},[16,300,301],{},"The demo showed side-by-side comparisons of traditional vs. CreditSense scoring for underserved applicants, demonstrating how the model correctly identifies creditworthy individuals that traditional systems reject.",{"title":85,"searchDepth":86,"depth":86,"links":303},[304],{"id":115,"depth":86,"text":116,"children":305},[306,307],{"id":123,"depth":140,"text":124},{"id":130,"depth":140,"text":131},"https://creditsense-demo.example.com",[310,321,330],{"name":311,"role":312,"bio":313,"links":314},"Roberto Morales","Team Lead & Data Scientist","Data scientist passionate about responsible AI and financial inclusion.",[315,317,319],{"platform":151,"url":316,"label":153},"https://linkedin.com/in/roberto-morales",{"platform":155,"url":318,"label":157},"https://github.com/rmorales",{"platform":159,"url":320,"label":161},"https://twitter.com/rmorales_ai",{"name":322,"role":323,"bio":324,"links":325},"Emma Johansson","ML Engineer","ML engineer specialising in fairness-aware machine learning and model interpretability.",[326,328],{"platform":155,"url":327,"label":157},"https://github.com/emmajohansson",{"platform":151,"url":329,"label":153},"https://linkedin.com/in/emma-johansson-ml",{"name":331,"role":332,"bio":333,"links":334},"Ahmed Hassan","Full-Stack Developer","Full-stack developer building ethical fintech products that expand access to financial services.",[335,337,339],{"platform":155,"url":336,"label":157},"https://github.com/ahmedhassan",{"platform":151,"url":338,"label":153},"https://linkedin.com/in/ahmed-hassan-dev",{"platform":181,"url":340,"label":183},"https://ahmedhassan.dev",{},"/hackathons/fintech-hackathon-2024/teams/team-smartledger","3rd","An explainable AI credit scoring system that combines traditional financial data with alternative data sources to improve lending decisions for underserved populations, while providing clear explanations for every decision.","CreditSense","https://github.com/team-smartledger/creditsense",{"title":284,"description":85},"hackathons/fintech-hackathon-2024/teams/team-smartledger",[200,350,351,278,204,352],"scikit-learn","SHAP","PostgreSQL","x1jFPVe8Lu-D_OvlzXPHOLoj_novBslKTh6bjv-_81c"]