FinFluence.ipynb

michaelml.dev / Michael_Portfolio.ipynb

AI-powered financial literacy platform that turns short-form video education into a tokenized economy. Sentence transformers validate content, custom Solana SPL tokens reward engagement. Built at SwampHacks XI.

[ ]

code · FinFluence

project = load_project("finfluence")
project.summary()

Output

FinFluence

SwampHacksFastAPISentence TransformersSolanaMongoDBReactTypeScriptDockerWeb3AI

[ ]

code · Problem definition

project = load_project("finfluence")
project.problem()

Output

ProblemShort-form financial content is easy to consume but difficult to verify, reward, and organize around genuine learning.

ApproachValidate uploads with sentence-transformer similarity, stream video from MongoDB GridFS, and reward qualified engagement with a Solana SPL token.

OutcomeDelivered an integrated multi-service prototype during the 36-hour SwampHacks XI build and documented the latency, streaming, and token-design lessons.

[ ]

code · Constraints

project = load_project("finfluence")
project.constraints()

Output

Constraints

Video validation could not block the upload experience.
Large media required chunked storage and byte-range delivery.
Rewards needed protections against shallow engagement and automated abuse.

[ ]

code · Role and implementation

project = load_project("finfluence")
project.implementation()

Output

Role and implementation

My role: Built the multi-service hackathon prototype with the team, connecting the FastAPI pipeline, React experience, content validation, storage, and token workflow.

Ran semantic content checks asynchronously after upload.
Stored video with MongoDB GridFS and served a short-form React feed.
Connected engagement calculations to a non-custodial Solana token flow.

[ ]

code · Architecture

project = load_project("finfluence")
project.show_architecture()

Output

Architecture overview

Validate uploads with sentence-transformer similarity, stream video from MongoDB GridFS, and reward qualified engagement with a Solana SPL token.

The documented project does not claim a separate architecture artifact.

[ ]

code · Demo and media

project = load_project("finfluence")
project.media()

Output

[ ]

code · Evaluation

project = load_project("finfluence")
project.evaluation()

Output

Evaluation

Validated the end-to-end upload, classification, streaming, and wallet flow during the hackathon.
Used content-relevance scoring and heuristic engagement checks rather than claiming educational efficacy.

[ ]

code · Results

project = load_project("finfluence")
project.results()

Output

Results

Produced a working multi-service prototype in a 36-hour hackathon window.
No user-adoption or learning-outcome metric is claimed.

[ ]

code · Tradeoffs and failures

project = load_project("finfluence")
project.tradeoffs()

Output

Tradeoffs

Token rewards can motivate participation but also create incentives for gaming.
Background validation improves responsiveness while delaying final publication decisions.

[ ]

code · What I would improve

project = load_project("finfluence")
project.improvements()

Output

Improvements

Run educator-reviewed quality evaluations and longitudinal learning studies.
Strengthen fraud detection and make reward policy easier to audit.

[ ]

code · Links and repository

project = load_project("finfluence")
project.links()

Output

GitHub Demo Project page

Role and implementation

My role: Built the multi-service hackathon prototype with the team, connecting the FastAPI pipeline, React experience, content validation, storage, and token workflow.

Ran semantic content checks asynchronously after upload.

Stored video with MongoDB GridFS and served a short-form React feed.

Connected engagement calculations to a non-custodial Solana token flow.