Skip to content
View alvenyuka's full-sized avatar
🎯
Building
🎯
Building
0 followers · 2 following

Block or report alvenyuka

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
alvenyuka/README.md

Hi, I'm Alven Yuka 👋

CPA Finalist working at the intersection of finance and data science, building the credit-risk and fraud models that sit downstream of development-finance operations.

LinkedIn Email

Projects

Project What it does Result
Credit Risk Scorecard (live) From-scratch WoE/IV and logistic regression validated line-for-line against scikit-learn on 307,511 real Home Credit applicants, plus a LightGBM benchmark 0.7774 AUC (LightGBM), 0.9985 correlation vs sklearn
Fraud Detection System XGBoost fraud classifier on 6.3M PaySim mobile-money transactions: balance-discrepancy feature engineering, isotonic calibration, walk-forward validated across 4 folds 99.85% precision / 99.56% recall
Financial-Analyst Three-statement models and DCF valuations built from primary-source SEC filings, with a validation tab tying every historical line back to source Fully source-linked
Stock-Portfolio-Tracker-Analytics-Engine Portfolio risk/performance analytics engine in Excel: VaR/CVaR, CAPM, Black-Litterman optimisation, tax-aware rebalancing 23-test validation suite

Stack

Python Pandas scikit-learn XGBoost SHAP SQL Excel Power BI

Credit risk: WoE/IV, scorecard development, GINI/KS/PSI, IFRS 9 ECL. Fraud: imbalanced classification, cost-sensitive thresholding, PR-AUC-first evaluation. Finance: GAAP/IFRS, 3-statement modelling, DCF valuation.

Open to Credit Risk Analyst, Data Analyst, and Financial Data Scientist roles.

📫 alvenyuka2@gmail.com · 💼 LinkedIn

Pinned Loading

  1. Financial-Analyst Financial-Analyst Public

    Company financial analyses built from primary-source filings: three-statement models, DCF valuations, scenario toggles. Each workbook has a validation tab that ties every historical line to its sou…

  2. Fraud-Detection-System Fraud-Detection-System Public

    Fraud classifier on 6.3M PaySim mobile-money transactions. XGBoost at 99.85% precision / 99.56% recall on a 132K-row time-based holdout, verified end-to-end by re-running the training pipeline agai…

    Jupyter Notebook

  3. Stock-Portfolio-Tracker-Analytics-Engine Stock-Portfolio-Tracker-Analytics-Engine Public

    Paper portfolio of 16 stocks tracked in Excel 365. Risk and performance analytics: CAPM, parametric/historical/Monte Carlo VaR, CVaR, Sharpe/Sortino/Calmar, Black-Litterman optimisation, tax-aware …