muhtr

1. Developed predictive models to estimate crypto token price volatility using time series analysis and Bayesian regression, improving forecasting accuracy by 15%. 2. Led the design and execution of statistical experiments (A/B Testing, ANOVA) for blockchain-based startups to evaluate new product features. 3. Built machine learning pipelines (classification & clustering) to detect anomalous wallet behavior and potential crypto fraud patterns. 4. Conducted exploratory data analysis (EDA) and built custom dashboards for clients tracking user growth, retention, and DeFi activity. 5. Created data visualizations (Plotly, Seaborn, Matplotlib) to explain token flow, staking trends, and smart contract usage to non-technical stakeholders. 6. Helped clients define and track key metrics (KPIs) for fundraising, DAO governance, and community growth using SQL and Python automation. Tech Stack: Python (Pandas, NumPy, Scikit-learn, PyMC3) • SQL • MongoDB • Jupyter • Tableau • Streamlit • Google Cloud Platform • Git

1. Analyzed on-chain wallet behavior from Ethereum and BNB Chain to detect user churn patterns, using clustering and cohort analysis in Python. 2. Built and maintained interactive dashboards (using Plotly & Streamlit) tracking DEX trading volumes and token transaction trends across 5 chains. 3. Conducted A/B testing for NFT drop campaigns and used ANOVA to determine statistical significance of user retention improvement (p < 0.05). 4. Designed and executed Bayesian models to forecast short-term token volatility based on price history and social sentiment (from Twitter API). 5. Created SQL-based KPI reports for DAO governance data: proposal participation, wallet voting power, and stake-to-vote ratios. 6. Partnered with Web3 startups to translate product needs into data-driven metrics, aligning business and tech. Tech Stack: Python (Pandas, NumPy, Scikit-Learn, Matplotlib) • SQL • MongoDB • BigQuery • Streamlit • Plotly • Google Sheets • Jupyter Notebook