Hi, I’m Lijoka Adedoyin a *Data Scientist | Machine Learning Enthusiast*

I hold a bachelors degree in statistics and have over 2 years of experience in data science and over 4 years of experience in e-commerce analytics. My journey has equipped me with a unique blend of skills, enabling me to analyze complex data patterns, build predictive models, and optimize business strategies.

I am passionate about leveraging data to drive impactful decisions, particularly in the finance, medicine and e-commerce sectors. My goal is to create solutions that not only meet client needs but also contribute to safer and more efficient business environments.

Below are some of my key projects that illustrate my expertise in data science and machine learning. Each project highlights various skills and techniques I’ve mastered.

#Projects

**Recipe Popularity Predictor**

**Fraud Detection Model**

**Churn Prediction Model**

** Mobile Price Classification using SageMaker **

**Movie Recommendation system **

** Attendance Management system**

** Wine quality prediction **

** Customer segmentation for E-commerce**

Featured Projects

Credit Card Fraud Detection System

Machine Learning | Python | Imbalanced Data Handling Developed a high-accuracy fraud detection model using machine learning (XGBoost, Random Forest) to analyze transaction patterns. Processed 280,000+ imbalanced records with SMOTE and feature engineering, achieving 99.2% precision in identifying fraudulent transactions. Deployed as a scalable Flask API for real-time predictions, reducing false positives by 40% compared to traditional rule-based systems. Key Skills Demonstrated: Data preprocessing (Pandas, NumPy) Handling class imbalance (SMOTE, class weighting) Model optimization (GridSearchCV, ROC-AUC analysis) API deployment (Flask, Docker)

Customer Churn Prediction Model

Machine Learning | Python | Business Analytics Built a predictive model to identify at-risk customers with 87% accuracy, leveraging ensemble learning (XGBoost, Random Forest) on historical user behavior data. Processed 50,000+ records with feature engineering (RFECV, PCA) to isolate 12 key churn drivers, including engagement frequency and support ticket volume. Deployed as a Dash dashboard enabling proactive retention campaigns, reducing churn by 22% in a simulated SaaS environment. Key Skills Demonstrated: Data wrangling (Pandas, SQL) Feature importance analysis (SHAP, LIME) Model interpretability (precision-recall tradeoffs) Interactive visualization (Plotly, Dash)

View All Projects

Hire Me

"Let’s turn your ideas into reality. Available for freelance projects, collaborations, and full-time roles."

Contact Me!