PsycheCredit: Unsecured Lending App on Midnight

[Proposal setup] Proposal title

Please provide your proposal title

PsycheCredit: Unsecured Lending App on Midnight

[Proposal Summary] Time

Please specify how many months you expect your project to last

3

[Proposal Summary] Translation Information

Please indicate if your proposal has been auto-translated

No

Original Language

en

[Proposal Summary] Problem Statement

What is the problem you want to solve?

1. The current DeFi system is largely over-collateralized lending, which limits financial access.
2. On-chain data and sentiment data have not been securely harnessed to expand access to fair credit.

[Proposal Summary] Supporting Documentation

Supporting links

• https://github.com/ADA-BAMBOO/PsycheScore
,
• https://psychescore.ada-bamboo.com/
,
• https://t.me/Cardano_ECO_VN

[Proposal Summary] Project Dependencies

Does your project have any dependencies on other organizations, technical or otherwise?

No

Describe any dependencies or write 'No dependencies'

No dependencies

[Proposal Summary] Project Open Source

Will your project's outputs be fully open source?

Yes

Please provide here more information on the open source status of your project outputs

This project is publicly available under the MIT License. We are committed to making the source code completely open. You are free to use, copy, modify, and distribute the code, with no obligations.

[Theme Selection] Theme

Please choose the most relevant theme and tag related to the outcomes of your proposal

Lending

[Campaign Category] Category Questions

What is useful about your DApp within one of the specified industry or enterprise verticals?

In this POC version, we will provide a GitHub repository including:

• Open-source Smart Contract on the Midnight blockchain for unsecured loans/loans with low collateral.
• Source code of AI-powered borrower psychology questionnaire.
• API endpoints containing wallet history data and identity verification.
• An intuitive web demo interface.

What exactly will you build? List the Compact contract(s) and key functions/proofs, the demo UI flow, Lace (Midnight) wallet integration, and your basic test plan.

We will build the unsecured lending dApp with three core components:

• Compact Smart Contracts 1 (Public Layer): Manages the Liquidity Pool, repayment logic, and the interest rate mechanism based on the credit score.
• Compact Smart Contracts 2 (Private Computation Zone): This is where the AI/ML model calculates the credit score based on psychometric questionnaire answers, on-chain data, and identity verification, all without revealing the input data.
• User Interface: An intuitive interface connecting with a Midnight wallet (supporting Lace) for users to initiate lending/borrowing, complete the secure questionnaire, and perform identity verification.

Necessity:

• It addresses a core need of the next generation of DeFi – the ability to execute complex financial decisions (like credit) without compromising personal privacy.
• Midnight + Compact allows us to perform complex calculations with private data in a secure environment, then issue the verified result (the credit score) to the public ledger portion of Midnight to execute the transaction.

Novelty:

• AI/ML processes the Input Data and the Computation Process privately on Midnight to enable a public financial decision (the loan).
• We leverage personal ecosystem reputation in roles such as DRep/SPO/Ambassador (with the capacity to extend to other roles within Midnight as they are defined) as input variables for credit scoring, significantly reducing the barriers to DeFi participation for thousands of people.

How will other developers learn from and reuse your repo? Describe repo structure, README contents, docs/tutorials, test instructions, and extension points. Which developer personas benefit, and how will you gauge impact (forks, stars, issues, remixes)?

The core value for developers:

• DApp developers: They will benefit from reusing the tested smart contracts to rapidly deploy complex unsecured lending models.
• ZK & Midnight integration developers: They gain a practical template framework for integrating Compact Contracts and generating ZK-Proofs to securely process private data.
• AI/Data science developers in Web3: They will learn how to safely package and deploy machine learning models within Midnight's secure environment to serve decentralized financial decisions.
• Reputation and Identity system developers: They acquire a template to quantify on-chain reputation (SPO/DRep roles) and combine it with private behavioral data to build new trust models.

[Your Project and Solution] Solution

Please describe your proposed solution and how it addresses the problem

The prevailing collateralized lending model in current DeFi faces a core problem: it requires users to over-collateralize their funds, resulting in low capital efficiency. This not only significantly reduces the user's purchasing power but also creates major barriers to capital access, excluding highly reputable individuals (such as DReps or SPOs) who lack sufficient assets to use as collateral.

To solve this, Bamboo Team introduces the unsecured lending model, where psychometric profiles, transaction data, reputation, and contribution become the borrowable asset. The benefits of this model are significantly enhanced by utilizing Midnight's technology, ensuring that the sensitive data (such as psychometric answers, personal identity) necessary for credit scoring is processed securely within the Private Data Zone.

As a result, users can access capital based on their trustworthiness while maintaining absolute privacy and data integrity, ushering in a new era for DeFi.

How dApps work:

• Data Collection from Wallet Address: Upon accessing the dApp, the user connects their wallet so the system can collect data on their wallet history and on-chain behavior, such as the value of assets (Coins, tokens, NFTs) in the past and present, transaction volume, transaction frequency, and Staking rewards.
• Data Collection from Psychometric Questionnaire: After connecting their wallet, the borrower will answer a questionnaire designed by psychological experts and performed by AI to assess personality and behavioral traits directly related to the borrower's risk-taking tendency, patience, reliability and financial responsibility.
• Data Collection from Ecosystem Role: Following the psychometric questionnaire, the borrower will need to provide personal information and evidence proving their role within the Cardano/Midnight ecosystem, such as SPO, DRep, Ambassador, etc. These roles often have a determined income and high trustworthiness but are currently untapped to encourage active participation in DeFi.
• Data Security, Analysis, and Scoring: The raw data collected above never leaves the secure environment. The entire analysis process is conducted inside Secure Smart Contracts on Midnight. A separate ML model of ours will process the borrower's answers, and the sensitive weighting calculations will be performed within the Private Data Zone. From there, only the final credit score and anonymous parameters (zero-knowledge proof) confirming the validity of the calculation process are released publicly, ensuring the borrower’s personal information is never exposed while the result remains verifiable.
• Lending Mechanism: Based on the securely generated credit score, the maximum stablecoin loan amount the user can borrow and the interest rate—which is proportional to risk (those with high credit scores will be loaned more and enjoy lower interest rates)—are determined, all automatically managed by a smart contract on Midnight.

System architecture:

Uniqueness:

• Psychology Questionnaire by AI: One of the first projects to apply psychology to AI to integrate on Midnight to expand more DeFi application cases, credit assessment....
• Input Data Protection: Concealing sensitive data (psychometric questions, identity verification) and the computation process from the public ledger delivers high efficiency and extends application possibilities compared to basic anonymity models.
• Reputation Valuation: Combines wallet behavior, ecosystem roles (DRep, SPO, Ambassador, etc.), and psychology to create the most comprehensive credit score. This helps thousands of individuals dedicated to the ecosystem receive preferential treatment when participating in DeFi.

Beneficiaries - This reference dApp will provide an open-source PoC containing reusable building blocks for:

• ZK/Midnight Developers: They gain a practical framework for creating and integrating Compact Contracts for private computation and ZK-Proof generation.
• DeFi DApp Developers: They can reuse the tested lending/borrowing logic for unsecured loans and complex risk management.
• AI/Data Science Developers: They learn how to safely deploy ML models within the blockchain's secure environment.

Importance for Midnight:

• Demonstrating the Use Case: This dApp will prove Midnight's capability to solve real-world financial problems (credit) requiring high privacy.
• Integrated Testing Framework: It provides a crucial testing platform for the interaction between AI/ML integration on Midnight and the Compact Smart Contracts.
• Community Attraction: By offering a clear and reusable PoC, it will attract a new wave of developers to build data-protected applications on Midnight.

[Your Project and Solution] Impact

Please define the positive impact your project will have on Midnight ecosystem

The project provides a significant positive impact, focusing specifically on developer attraction and strengthening the underlying technology:

• Demonstrating the Viability of Private Computation: Create smart contracts that do the processing and data collection from the blockchain and transfer anything CPU and memory intensive via web3 (machine learning is computationally intensive), web3j or some other off-chain API to a traditional server for (credit scoring) privacy.
• Fostering Chain Interaction: The project provides a tested template framework for interaction within the private computation environment (Midnight) via ZK-Proof.
• Attracting ZK Developers: We offer an open-source, reusable PoC on how to implement data protection features for DeFi applications, lowering the barrier for developers who want to build on Midnight.

We are committed to sharing the results transparently and accessibly:

• Open Source: The entire PoC codebase will be publicly released on GitHub.
• Documentation: We will provide detailed guidance (README.md, DOCS.md) focusing on the methodology for enhancing privacy and the key deployment steps.
• Demo: We will provide an intuitive web interface for developers to easily test the secure data flow (from answering the questionnaire to ZK-Proof verification).

[Your Project and Solution] Capabilities & Feasibility

What is your capability to deliver your project with high levels of trust and accountability? How do you intend to validate if your approach is feasible?

The Bamboo Team represents the optimal synergy of deep technical expertise and extensive experience within the Cardano/Midnight ecosystem, making us the most suitable choice to successfully deliver this project:

• Stake Pool Operation: With over two years of experience running the BBO stake pool, operating a Midnight testnet pool for over a year, and creating multiple bots for on-chain data collection, we guarantee accurate on-chain data retrieval and API provisioning for the model.
• Our Tech Lead possesses high proficiency in AI/ML, capable of deploying end-to-end model life cycles using Python, R, TensorFlow, PyTorch, and LightGBM—from designing data pipelines (SQL, GraphQL, Docker) to cloud deployment (AWS/Azure/GCP). Furthermore, his many years in management at major financial institutions provide extensive knowledge of Basel compliance, regulatory frameworks, and automated underwriting at top-tier banks (TPBank, Viet Credit, OCB), which is crucial for the credit scoring component.
• Regarding Catalyst experience, we have a track record of completing two successful proposals: one in Fund 11 (1100034) focused on a Concept for a mobile application for on-chain data collection, and a proposal in Fund 13 (1300003) regarding open-source code for an AI governance chatbot for Cardano.
• In the Cardano/Midnight ecosystem, we have established a community of over 1.3K members dedicated to sharing information about the Cardano/Midnight ecosystem (https://t.me/Cardano_ECO_VN)..) We also actively promote and share knowledge about Midnight during events we organize or participate in. Cooperate with Cardano Vietnam to organize an event to share about Cardano and Midnight

Speakers introducing Cardano/Midnight at Bitget X Cardano: Saigon Ledger Night event

With this proposal, we have already deployed several demo products such as:

• Demo: https://psychescore.ada-bamboo.com/
• Psychometric Questionnaire V0.5 GitHub: https://github.com/ADA-BAMBOO/PsycheScore/tree/master/psychescore
• Smart Contract V0.1 GitHub: https://github.com/ADA-BAMBOO/PsycheScore/tree/master/psychescore-mn

[Final Pitch] Budget & Costs

Please provide a cost breakdown of the proposed work and resources

Milestone 1: 1 month

• Allocation: 1 Manager (30 hours/month) and 2 DEV (120 hours/month)
• 150 hours/month x 20 USD/hour = 3,000 USD

Milestone 2: 1 month

• Allocation: 1 Manager (30 hours/month) and 2 DEV (120 hours/month)
• 150 hours/month x 20 USD/hour = 3,000 USD

Milestone 3: 1 month

• Allocation: 1 Manager (30 hours/month) and 2 DEV (120 hours/month)
• 150 hours/month x 20 USD/hour = 3,000 USD

Other costs: 1,000 USD

• Including: Cost of renting tools, API, renting server

Total budget: 10,000 USD

[Final Pitch] Value for Money

How does the cost of the project represent value for the Midnight ecosystem?

This project represents a good use of funds because it invests in creating open-source, reusable tools to solve the biggest challenges in DeFi, becoming a reference application for Midnight.

Efficient Use of Funds:

• Creating Unsecured Lending Tools: The budget is focused on creating a complete PoC codebase demonstrating that Unsecured Lending is viable. This unlocks capital efficiency in DeFi by valuing Community Reputation (DRep/SPO/Ambassador, etc.) instead of collateral.
• Core Technical Model: Funds are used to develop and test high-value technical assets: the Compact Contract, a template running the ML Model for the psychometric questionnaire, and handling complex computations.
• Support for intuitive interface and comprehensive documentation: Developers can reuse our intuitive interface for easy management and testing of the unsecured lending model, guided by our thorough deployment instructions.

Breakthrough Value for Midnight:

• Private AI Use Case: This reference dApp provides a working blueprint for how to integrate Artificial Intelligence (AI) into Midnight to make financial decisions while protecting sensitive input data (psychometric answers).
• Validating Reusability: This PoC confirms that Midnight developers can use Compact Contracts to build sophisticated applications beyond just KYC or private voting—extending to advanced financial services—thereby accelerating adoption and diversifying the Midnight ecosystem.

[Self-Assessment] Self-Assessment Checklist

I confirm that the proposal clearly provides a basic prototype reference application for one of the areas of interest.

Yes

I confirm that the proposal clearly defines which part of the developer journey it improves and how it makes building on Midnight easier and more productive.

Yes

I confirm that the proposal explicitly states the chosen permissive open-source license (e.g., MIT, Apache 2.0) and commits to a public code repository.

Yes

I confirm that the team provides evidence of their technical ability and experience in creating developer tools or high-quality technical content (e.g., GitHub, portfolio).

Yes

I confirm that a plan for creating and maintaining clear, comprehensive documentation is a core part of the proposal's scope.

Yes

I confirm that the budget and timeline (3 months) are realistic for delivering the proposed tool or resource.

Yes

[Required Acknowledgements] Consent & Confirmation

I Agree

Yes