Insights Hub

FinTech Factory LunchTime Series โ€“ 3

BrownBag Series Recap

Date:ย  31 July, 2025

Speaker: Alya R Prastiti, Intern @ NUS FinTech Lab

This brownbag explored the complexities of Singaporeโ€™s Option-to-Purchase (OTP) workflow for residential property transactions, shedding light on the inefficiencies that persist. The discussion revealed how manual hand-offs, fragmented compliance checks, and legal constraints hinder efficiency and transparency, while also outlining pathways for digital transformation.

ย 

Mapping the Gaps: Understanding and Redesigning Property Transaction Workflows in Singapore

Understanding the Problem

The current OTP process involves multiple stakeholdersโ€”property agents, conveyancing lawyers, mortgage officers, and government agencies such as the Singapore Land Authority (SLA) and the Inland Revenue Authority of Singapore (IRAS). Despite the availability of digital tools, the workflow remains heavily reliant on manual steps. Lawyers, for instance, are required to conduct searches across various portals:

  • INLIS for title checks,

    ย 

  • eLitigation for litigation history,

    ย 

  • MinLawโ€™s e-service portal for bankruptcy searches, and

    ย 

  • STARS eLodgment for lodgments.

    ย 

This fragmentation creates delays and additional costs, often forcing practitioners to turn to third-party services. Moreover, the continued requirement for wet-ink signaturesโ€”mandated under current regulationsโ€”prevents the adoption of more efficient, paperless alternatives.

Challenges in the Current Workflow

The speaker summarized several structural bottlenecks:

  • Fragmented portals leading to duplicated effort.

    ย 

  • Absence of real-time notifications, slowing the flow of critical information.

    ย 

  • Mandatory wet-ink signatures, which prevent full digital adoption.

    ย 

  • Heavy compliance burdens, particularly AML/CFT checks and the retention of records for five years.

    ย 

These challenges collectively limit both efficiency and transparency, raising questions about the long-term sustainability of the current system.

Research Questions Raised

The session framed the inquiry around three guiding questions:

  1. What pain points most delay or compromise compliance and transparency?

    ย 

  2. Which digital capabilities do practitioners most value for efficiency?

    ย 

  3. How can digital tools be designed to integrate seamlessly with Singaporeโ€™s legal framework?

    ย 

These questions served as the basis for stakeholder interviews and practitioner-led design exercises, aimed at identifying where digital interventions could have the most meaningful impact.

Towards a Digital Solution

To address these gaps, the session proposed a two-tier digital solution:

  1. Integrated Due Diligence Platform

    ย 

    • A unified interface consolidating all searches and lodgments.

      ย 

    • Embedded KYC/AML checks and automated compliance workflows.

      ย 

  2. Real-Time Collaboration Dashboard

    ย 

    • A secure environment enabling property agents, lawyers, and regulators to coordinate seamlessly.

      ย 

    • Immediate updates on progress and compliance status.

      ย 

This dual approach aims to streamline workflows while ensuring regulatory compliance.

Future Research Directions

Looking ahead, the next phase of work must go beyond digitizing existing workflows to developing a blockchain infrastructure blueprint that complies with Singaporeโ€™s property laws while supporting both traditional sales and emerging fractional ownership models.

Key research areas identified include:

  • Fractional Ownership โ€“ Investigating how to legally structure, govern, and record shared ownership rights on-chain in a manner consistent with Singaporeโ€™s property regulations.

    ย 

  • Legal Entity Requirements โ€“ Exploring compliance frameworks for tokenized property ownership involving companies, trusts, or funds, ensuring alignment with KYC/AML standards and beneficial ownership rules.

    ย 

  • Dissolution & Re-Sale Processes โ€“ Designing enforceable and technically robust mechanisms for fractional stake resale, buyouts, or dissolution, including smart contractโ€“driven protocols that map onto existing conveyancing practices.

Key Takeaway

The session underscored that the future of property transactions in Singapore will hinge on bridging law and technology. While digitization can streamline existing workflows, the transformative leap lies in creating a blockchain-based infrastructure that enables secure, compliant, and legally recognized property salesโ€”including fractional ownership models. Progress in this space will depend on targeted research into ownership structures, and legal entity compliance, paving the way for a tokenization-ready property market.

FinTech Factory LunchTime Series โ€“ 3 Read More ยป

FinTech Factory LunchTime Series โ€“ 2

BrownBag Series Recap

Date: 24 June, 2025
Speaker: Ryo Seah, Intern @ NUS FinTechLab

This BrownBag session focused on automating donor due diligence for philanthropic organizations, presenting a proof-of-concept OSINT pipeline. The discussion examined technical challenges including LLM hallucinations and  clustering thresholds while highlighting solutions such as hierarchical clustering, source reliability scoring, and integration with CRM systems for scalable risk management.

An Automated Pipeline for Generating Open Source Intelligence Dossiers for Donor Vetting

Understanding the Problem

Philanthropic organizations face a complex challenge in ensuring comprehensive donor due diligence while managing reputational risks. Current workflows are often manual, fragmented, and time-consuming, requiring staffs to piece together unstructured data from scattered sources. To address these inefficiencies, the lab explored how intelligent automationโ€”combining web scraping, large language models, and clustering techniquesโ€”can streamline the due diligence process and improve the accuracy and scalability of donor profiling.

Key Challenges

Two persistent challenges stood out:

  1. LLM Hallucinations โ€“ While LLMs are effective at structuring scraped data, they occasionally produce unsupported claims.

    • Solution: Establishing a โ€œchain of trustโ€ by tying each fact directly to its original source.

  2. Ambiguous Profiles โ€“ Similar or identical names often led to merged donor records.

    • Solution: Agglomerative clustering with semantic embeddings flagged potential overlaps for human review.

Other hurdles included API rate limits, blocked scraping on certain sites, and the scalability of processing larger name lists.

Technical Implementation

The demonstrated pipeline (Stage 1: OSINT Automation) follows a three-step workflow:

  • Search: SerpAPI for Google results, Playwright for scraping dynamic content.

  • Aggregate: LLMs structure data into clean key-value pairs, removing noise.

  • Cluster: Embeddings identify duplicate or ambiguous profiles, generating YAML outputs for PDF dossiers.

This approach ensures traceability by linking every fact to its source, significantly reducing hallucination risks.

Research Questions & Discussion

The BrownBag session not only outlined the proof-of-concept pipeline but also raised critical questions from the internal audience, reflecting both technical and strategic considerations:

  • How can the system be made more user-friendly, perhaps through a GUI interface with simple input fields rather than relying on command-line operations?

  • What statistical approaches (e.g., elbow method) could refine clustering thresholds and improve the disambiguation of donor profiles?

  • Can Named Entity Recognition (NER) be integrated to automatically filter out irrelevant paragraphs during web scraping?

  • How should we design a source reliability scoring system that prioritizes information from more authoritative and trustworthy domains over less reliable sources?

  • Would a saturation-based link collection approach, instead of a fixed link limit, improve coverage and accuracy of profiles?

Key Takeaways

  • Proof of Concept: Successfully processed 5 names per batch with 70โ€“80% scrape success, producing structured and verifiable YAML/PDF outputs.

  • Audience Feedback: Raised crucial ideas for GUI development, clustering refinements, NER, and open-source LLM exploration.

  • Future Roadmap: Enhancements include source reliability scoring, fuzzy matching across sources, and integration of risk indicators.

  • Strategic Outlook: Beyond automation, the project aims to build a full Intelligence & Risk Engine to support long-term donor due diligence.

The session closed with a shared recognition: while automation cannot replace human oversight, it can significantly reduce repetitive effort, improve accuracy, and enable staff to focus on high-value decision-making.

FinTech Factory LunchTime Series โ€“ 2 Read More ยป

FinTech Factory LunchTime Series – 1

BrownBag Series Recap

Date: 25 May. 2025
Speaker: Reshma Balaraman, Research Associate, NUS FinTechLab

This BrownBag session explored retail investor behavior in financial markets, analyzing how everyday traders respond to wins, losses, and changing market conditions. Using on-chain transaction data and controlled experiments on the NUSWAP platform, the discussion highlighted how behavioral biases like overconfidence, loss aversion, and the disposition effect shift across different environmentsโ€”and how these insights can inform both market design and investor protection.

Understanding the Problem

Retail participation in financial markets is accelerating, driven by mobile apps and real-time platforms. While this democratization has opened opportunities, it has also introduced challenges:

  • Design features such as push notifications and gamified interfaces shape how traders think, react, and decide under pressure.

  • Unlike educational settings, retail traders rarely receive behavioral feedback, leaving them vulnerable to biases that influence decision-making.

  • At scale, these individual tendencies can aggregate into market-wide instability.

Understanding these dynamics is therefore criticalโ€”not only for academic research, but also for consumer protection and regulatory priorities.

Key Behavioral Biases Studied

The session examined five core biases, operationalized through trading signals:

  • Disposition Effect โ€“ Selling winners too early, holding losers too long.

  • Gamblerโ€™s Fallacy โ€“ Expecting a win after a losing streak.

  • Loss Aversion โ€“ Losses felt more intensely than gains, causing hesitation.

  • Overconfidence โ€“ Past success inflates perceived trading skill.

  • Risk Aversion โ€“ Preference for smaller bets after losses.

Bias detection relied on on-chain behavioral data such as trade timing, position size changes, and delays between trades.

Dataset & Methodology

  • 200,000+ transactions, across 20,000+ wallets over 12 months.

  • Filtering excluded bots and inactive traders, yielding a focused sample of 2,031 active wallets.

  • Biases were detected directly from trading patterns, not surveys or self-reports.

This approach allowed for robust behavioral inference at scale, grounded in real-time decision-making.

Key Findings

  1. Context-Dependent Biases
  • Disposition effect strongest in calm markets (65% of traders), but drops in high volatility (15%).

  • Biases are dynamic, not fixed; traders adapt to changing conditions.

  1. Overconfidence & Market Regimes
  • Surges in momentum markets (โ‰ˆ60%), but falls in mean-reversion environments.

  • Can improve outcomes during strong trends, but backfires when conditions flip.

  1. Loss Aversion & Drawdowns
  • Loss-averse traders experience much deeper drawdowns (~20% vs ~5%).

  • Reluctance to cut losses turns small setbacks into long-term risks.

  1. Biases as Double-Edged Swords
  • Behaviors labeled โ€œirrationalโ€ in calm markets may protect traders in volatile ones (e.g., avoiding whipsaws).

Role of NUSWAP: From Observation to Intervention

The discussion emphasized why NUSWAP was built as a research platform:

  • Streams live market data to simulate real pressure.

  • Provides a risk-free environment for participants.

  • Enables both manual and algorithmic trading, allowing structured strategies.

Through SIMTRADE contests (NUS, FGV Brazil, Morgan State University), NUSWAP has generated datasets from 125+ participants, confirming its potential as a behavioral finance lab.

Research Questions & Discussion

During the session, the audience raised key questions for future exploration:

  • How can nudges be designed to prevent harmful bias-driven behavior?

  • Can interventions be personalized to different trader profiles?

  • What frameworks would allow integration of behavioral safeguards into consumer protection regulation?

  • How can NUSWAP be scaled across universities to build a global dataset for collaborative research?

Key Takeaways

  • Retail investors matter: Their behaviors influence not only individual outcomes but also market dynamics.

  • NUSWAP bridges the gap: From detecting biases to testing interventions in a controlled yet realistic setting.

  • Towards investor protection: The long-term goal is to design platforms and policies that support safer, smarter trading.

ย 

FinTech Factory LunchTime Series – 1 Read More ยป

NUS FinTech Society Wins Big at ETH Oxford 2025

Congratulations to the NUS FinTech Society (FTS) Blockchain team on their success at the ETH Oxford Competition 2025! Over the course of the event, they demonstrated focus, skill, and creativity, earning three awards across multiple tracks.ย Their achievements reflect the dedication and talent of the team and offer a glimpse into the future of blockchain and decentralized finance.

Let’s hear from the winners about their experience at ETH Oxford 2025.

ETH Oxford 2025

ETH Oxford is the largest blockchain hackathon at Oxford University, organized annually by the Oxford Blockchain Society. Held at the university’s prestigious Mathematical Institute, with a prize pool exceeding $100,000 USD, this three-day event brings both experienced and new developers to build and collaborate together.

In the midst of a chilly February, five representatives across three teams from NUS Fintech Society hacked tirelessly for around 40 hours in Oxford. Their hard work paid off when each team managed to win their targeted bounty prize, with one managing to win the main consumer prize, totalling to more than $10,000 USD, roughly 10% of the total prize pool.

Moreover, the winners of the main tracks were invited to an exclusive gala dinner at the prestigious Rhodes House, home to one of the world’s most distinguished scholarship programs – the Rhodes Scholarship, a symbol of academic excellence at Oxford University. The historic venue provided an elegant backdrop for attendees to celebrate their collective success, network with prominent Web3 founders and investors, and strategize their next steps moving forward.

Left to Right: NUS SoC team - Jefferson Lee Chun Yin, Jerial Chan Zhi Yang, Kevin Lim Teng Hong

The Process

The hackathon officially kickstarted at 6pm on 7 February 2025. Our efforts, however, started one week before. Once some of the problem statements were released, we started researching, learning and bouncing ideas off each other. Two days before the hackathon commenced, Jeff reached out to Philip, the person in charge of the Flare track, seeking his opinions on our idea, requesting API keys to their data connector, and inquiring about other related technical details, and Philip was kind enough to assist us.

For the next 3 days, we spent our days hacking at the basement floor of the Mathematical Institute, while our nights were spent at the hacker house, provided by the ETH Oxford team.

Our daytime hours were packed with intense hacking sessions, with a few insightful workshops. From time to time, we also looked for representatives from each of our bounty tracks to seek technical help as well as feedback. The organising team kept us well fed with freshly cooked paella for lunch and on-the-spot wood fired pizzas for dinner. It was fantastic!

However, one major challenge that we faced was the instability of WiFi connection. With so many participants connected to the same network, internet bandwidth struggled. Determined to find a more reliable connection, we constantly relocated, from the main hacking area to an empty workshop room. We eventually went up to the main lobby, which was where we discovered the best WiFi spot.

The night before our submission, we powered through the final stretch with instant coffee and instant noodles, making sure that our project was completed and of the highest quality before submission. We took turns taking short naps intermittently till 6am, then we ultimately succumbed to the sleep demons for the next 2-3 hours. The next morning, we managed to fix the last few bugs, prepared our presentation slides, and filmed our demo video. Then, we headed down to the venue one last time for our final presentation. And finally, it was over!

The Outcome

These are the 3 winning projects submitted by the teams.

FlareGate

by Jerial Chan Zhi Yang, Jefferson Lee Chun Yin, Kevin Lim Teng Hong

1st for main track (consumer), 1st for Flare Track

FlareGate is a decentralized peer-to-peer (P2P) platform designed to facilitate seamless on-ramping and off-ramping between fiat currencies and cryptocurrencies. Leveraging Flare Network’s Data Connector (FDC), FlareGate ensures trustless and efficient transactions by securely integrating off-chain data into on-chain smart contracts.

More information can be found here.

NUS SoC Team - Left to Right: Jerial Chan Zhi Yang, Jefferson Lee Chun Yin, Kevin Lim Teng Hong

Guess The Human

by Chua Wei Rong (NUS), Jason Chai Jian Hao (University of Bristol)

1st for AirDao Track

Guess The Human is a disruptive new blockchain-based AI-driven Turn Based Social Deduction game where players attempt to identify the human-controlled player among AI agents moving randomly on a 2D grid. The game consists of two main roles: players and guessers.

More information can be found here.

Left to Right : Chua Wei Rong (NUS SoC Team), Jason Chai Jian Hao (University of Bristol)

Mina Verify

by Marcus Pang Yu Yang (NUS SoC Team – No photo taken)

2nd for Mina Track

This project implements the BLS12-381 signature scheme, enabling developers to verify such signatures through MINA’s smart contract. This enables important use-cases such as cross chain bridges, allowing other chains to settle on MINA, and signature aggregation.

More info can be found here.

NUS FinTech Society Wins Big at ETH Oxford 2025 Read More ยป

“Your Tomorrow Starts Here” – NUS Computing 2024

ย 

We are delighted to share the highlights from the vibrant “Your Tomorrow Starts Here” hosted by NUS Computing on May 11th, 2024. It was truly a day filled with inspiration and exploration, welcoming around 500+ participants in this session.

The day was packed with engaging sessions which included a tour to NUS FinTech Lab. During the tour to our lab, these students were warmly welcomed by our interns and our NUS Fintech Society key members who showcased the innovative projects and engagement opportunities for students to explore in the fintech space.

Key questions were addressed, such as developing and showcasing research projects to global audiences, connecting with industry leaders, participating in hackathons, and securing internships while studying full-time.

Through insightful presentations, interactive Q&A sessions, and engaging project showcases, attendees gained a clear understanding of how they can actively shape their future by joining NUS Computing.

We’re also thrilled that the complimentary tumblers and notepads were a hit, adding an extra layer of excitement to the day!

A big thank you to everyone involved for making this event a milestone. We look forward to seeing the great achievements our future leaders will accomplish as they begin their journeys with us. Hereโ€™s to a future driven by innovation and collaboration!

NUS NUSComputing Fintech Innovation YouCanNUSComputing Technology NUSFinTechLab NUSFinTechSociety FutureLeaders InnovationInFinance Enterpreneurship StudentStartups InternshipOpportunities

“Your Tomorrow Starts Here” – NUS Computing 2024 Read More ยป

Project Demo with Ripple

We were privileged to welcomeย Lauren Weymouthย andย Nasri N.ย fromย Ripple‘s University Blockchain Research Initiative (UBRI) toย NUS FinTech Labย on April 16th. The visit commenced with a brief presentation by Prof.ย Jungpil Hahn, outlining our commitment to thought leadership, support for innovative research projects, and our role in shaping the fintech ecosystem through education.

Our lab’s interns, members of theย NUS Fintech Society, andย NUS Computingย student researchers seized the opportunity to showcase some of their innovative research projects, demonstrating the innovative spirit and intellectual rigor of our vibrant community within theย National University of Singapore.

Highlights included:
1. Fractionate – Property Asset Tokenization.
2. Beyond Border – Exploring Maximal Extractable Value and risks in cross-domain CEX-DEX arbitrage. (Research)
3. KataraFi โ€“ P2P cross-currency payments.
4. NUSwap – ย Educational Crypto Exchange platform.
5. Large Value Payment System Simulator for academic and Central Bank research
6. Verifin – Innovating blockchain transaction security with identity auto-validation.
7. And last but not least, research into more open and reproducible methods of applying Large Language Models (LLM) to finance.

The partnership betweenย NUS FinTech Labย andย Rippleย is setting the stage for revolutionary advancements in FinTech.

A huge thank you to our dedicated students, theย NUS Fintech Society, and theย NUS FinTech Labย team for their outstanding contributions.

We are not just anticipating the future; we are actively crafting it and are exhilarated by the possibilities that await!

#NUSย #NUSFinTechLabย #Rippleย #UBRIย #FinTechย #AIย #Innovationย #Blockchainย #Technologyย #FutureOfFinanceย #Researchย #AcademicExcellence

Project Demo with Ripple Read More ยป

Coffee Chat Session with Standard Chartered

Delving into Fintech’s Future with SC Ventures: A Glimpse from the NUS FinTech Brew Chat

In the third edition of theย #NUSย FinTech Brew Chat, we were honored to hostย Santosh Patelย andย Aaron Gwakย fromย SC Ventures by Standard Chartered. The session, moderated astutely by Professorย Jungpil Hahn, Director at theย NUS FinTech Lab, offered unparalleled insights into the ever-evolving fintech landscape.

Key Takeaways from Our Chat:
1. Choosing the Right Startups: SC Ventures values startups that adeptly integrateย innovative technologies with team diversity and a vision for scalability. Beyond these, startups should possess a fervent passion, deep curiosity, resilience, and practical execution capabilities. The emphasis lies in comprehending market needs, frequent validation, and the agility to evolve.

2. Navigating the Startup Arena: To thrive in the startup space, aligning personal strengths with the mission of the startup is vital. The foundation rests on introspection, deliberate networking, practical experiences, and an adaptable entrepreneurial spirit. Continual updating on industry trends and tech innovations becomes the keystone for lasting relevance.

3. Tackling Fintech Challenges: The fintech sphere, while lucrative, is riddled with complexities. From mastering multifaceted regulatory frameworks to ensuring cybersecurity and building enduring trust, the challenges are manifold. Startups must also juggle capital acquisition, seamless scalability, and uphold stringent data privacy standards. Effective startup evaluation zeroes in on solution viability, tech competency, and clear success metrics. For those with a global outlook, adeptness at varied regulatory landscapesโ€”backed by legal expertise, meticulous compliance, and productive international partnershipsโ€”is indispensable.

By providing these profound insights,ย SC Ventures by Standard Charteredย encapsulates the essence of fintech’s future and offers a roadmap for those navigating its multifaceted terrain.

We extend our heartfelt gratitude to theย #SCVenturesย team for enriching us with their invaluable insights. A special thanks to theย NUS Fintech Societyย for their active participation, ensuring that the vibrancy of our fintech community at theย National University of Singaporeย never dims.ย NUS FinTech Labย remains committed to fostering a robust and informed fintech community here at theย National University of Singapore.

To many more sparkling and collaborative dialogues!

NUS #Fintech #CoffeeChat#Fintechecosystem #SCVentures#Innovation#StartUps#FutureofStartup

Coffee Chat Session with Standard Chartered Read More ยป

Lunch and Learn – Ripple

Lunch and Learn with Ripple

NUS FinTech Labย were honoured to share their insights atย Rippleย Singapore on 16 May in a workshop onย #Smartย Contracts andย #DAO! Marcus Pang, a student fromย NUS Fintech Societyย kicked off with an introduction toย #smartcontractsย and Decentralised Autonomous Organisations (#DAO), sharing fascinating use cases and applications, then inspired everyone with a demo of the Societyโ€™s latest project, โ€œABC DAOโ€

Professorย Jungpil Hahn,ย NUS FinTech Labย Director, explored the power ofย #DAOย and their impact on organisations, sharing simulated environment modelling results that show the perfect balance ofย #DAO, combining unity and diversity. The workshop Q&A catalysed deep discussion about the impact ofย #AI on humanity. Collaboration or replacement? Huge appreciation toย Ajshia Najafianย andย Rippleย Singapore team for organising this event! Connect and collaborate atย NUS FinTech Labย to shape the future ofย #fintech! #singaporefintechย #smartcontractsย #daoย #rippleย #nus

Lunch and Learn – Ripple Read More ยป

Coffee Chat – Mastercard

Coffee Chat with Mastercard

Fintech Brew: Mastering Generative AI with Mastercard at NUS FinTech Lab

Kudos toย Donghao Huang, VP of R&D at Mastercard, for sharing his expertise on AI, Web3, and cutting-edge Mastercard initiatives at our Fintech Brew event on April 20th at NUS FinTech Lab!

Key takeaways from this session:
1. Leveraging AI to delight customer experiences
2. Unlocking the potential of tokenization
3. Embracing AI technologies to enrich students’ learning experiences.

Donghao Huang‘s focus on innovation and experimentation as success drivers resonated with all attendees.

We’re grateful for your invaluable knowledge and wisdom.
Stay connected, stay inspired!

#Mastercardย #NUSย #AIย #Web3ย #Tokenizationย #innovationย #fintechย #coffeechat

Coffee Chat – Mastercard Read More ยป

Coffee Chat with Blackrock

Coffee Chat with Blackrock

A huge thank you to our BlackRock speakers, Marko and Ee Chuan, for sharing these insights! Innovation and Experimentation โ€“ โ€œBe adaptable, resilient, innovate to create products which fulfil an unmet market needโ€. Being a Fiduciary โ€“ โ€œAlways act in the best interest of clients, prioritize their needs over yours, build trust and long-term relationshipsโ€. Your expertise and experiences have truly inspired our audience, and we are grateful for your time spent with our students in fostering a deeper understanding of these essential topics in the fintech industry. #BlackRock #Aladdin #FinTech #RiskManagement #CoffeeChat #NUS

Gallery

Coffee Chat with Blackrock Read More ยป

Scroll to Top