I made a tutorial for an AI agent where I built an AI-powered blockchain analytics platform (https://www.youtube.com/watch?v=ceRZWLkxEbU) built with CrewAI that analyzes crypto wallets across Ethereum, Polygon, BSC, Arbitrum, and Base.
Uses 4 specialized agents - Portfolio Analyst, Transaction Specialist, Investment Strategist, and Intelligence Synthesizer - working sequentially to process on-chain data via Zapper API.
Delivers good reports with portfolio composition, risk assessment, behavioral patterns, and investment recommendations through CLI and Streamlit interfaces with real-time tracking and downloadable outputs.
Try it out: https://onchain-ai-agent.onrender.com/
Github code: https://github.com/Emarhnuel/Onchain-AI-agent
Experienced Data Analyst, bringing your data to life
6
Followers
Experienced Data Analyst, bringing your data to life
This project takes a fraud-detection model built in a notebook and turns it into a small, runnable system you can demo and deploy locally. In my workflow, I start with the notebook, save a single artifact, then wrap it with an API, a UI, and basic monitoring.
1 (https://1). Train and evaluate a model on creditcard.csv
2. Save a deployable artifact (.pkl)
3. Serve predictions through a FastAPI backend
4. Provide a Streamlit UI for manual testing and batch scoring
5. Log predictions and feedback labels for monitoring
6. Run basic drift checks and export feature importance for sanity checks
What Problem This Solves
Fraud detection is a highly imbalanced classification problem, so "accuracy" is usually misleading. What you typically want is:
1 (https://1). a risk score (fraud probability) per transaction
2. a decision policy (threshold) you can tune to match operational goals (precision/recall tradeoff)
3. serving layer so the model works outside Jupyter
4. a monitoring loop so you can detect drift and decide when to retrain
1
163
Built an end-to-end e-commerce recommendation system using FastAPI, SQLite, and custom ML ranking models. The project supports content-based, collaborative, and hybrid recommendations, ingests a real product catalog dataset, seeds user interactions for personalization, and exposes a browsable frontend plus documented REST APIs.
1
77
This project was executed through the use of Microsoft excel, it shows trends and metrics of Air crashes from inception till date
3
3
229
This project highlights key metrics in car sales and pricing, with insights into dealership distribution, sales performance, revenue, and customer preferences.
AI Engineer creating AI systems such as Chatbots & AI agents
AI Engineer creating AI systems such as Chatbots & AI agents
An Adverse Drug Effect Predictor Using AI
By applying a machine learning approach to Rheumatoid Arthritis therapy, Adept-AI (Adverse Drug Effect Predictor - Artificial Intelligence) aims to improve prescription outcomes of Rheumatoid Arthritis drugs by predicting how individual patients will respond to medication based on demographic factors.
1
65
RAG based Chatbot for Sales Assistant with streamlit.
0
55
Web scraping and Automation with selenium
0
56
Inventory chatbot development and integration with Whatsapp via Twilio.