Welcome to my WorldQuant Applied Data Science Lab repository! Here, I document my experience in this intensive data science program through eight unique projects, each tailored to address real-world challenges using data science techniques.
🎓 Certification Progress: I’m currently enrolled in the WorldQuant Applied Data Science Lab, where I’ve been applying theoretical knowledge in hands-on projects across a variety of domains. Each project folder contains documentation, code explanations, and visualizations.
Here’s a snapshot of each project included in this repository, with individual folders containing detailed Markdown documentation for code, approach, and outcomes.
-
🏡 Housing in Mexico
- Objective: Analyze whether property size or location impacts real estate prices more.
- Methods: Data cleaning, visualization, and correlation analysis.
- Skills Highlighted: Exploratory Data Analysis (EDA), Data Preprocessing.
-
🏙️ Apartment Sales in Buenos Aires
- Objective: Build a linear regression model to predict apartment prices.
- Methods: Linear regression, imputation, and categorical encoding.
- Skills Highlighted: Linear Modeling, Overfitting Reduction.
-
🌍 Air Quality in Nairobi
- Objective: Predict air quality levels using ARMA time-series modeling.
- Methods: ARMA model, MongoDB extraction, hyperparameter tuning.
- Skills Highlighted: Time Series Analysis, Model Optimization.
-
🏚️ Earthquake Damage in Nepal
- Objective: Predict building damage after earthquakes.
- Methods: Logistic regression, decision trees, and SQLite database extraction.
- Skills Highlighted: Classification, Bias Analysis, Model Evaluation.
-
📉 Bankruptcy Prediction in Poland
- Objective: Forecast bankruptcy likelihood in companies.
- Methods: Random forest, gradient boosting, imbalanced data handling.
- Skills Highlighted: Precision & Recall Evaluation, Advanced Model Tuning.
-
📊 Customer Segmentation in the US
- Objective: Cluster US consumers based on spending patterns.
- Methods: K-means clustering, PCA, Plotly Dash dashboard.
- Skills Highlighted: Clustering, Dimensionality Reduction, Data Visualization.
-
🧪 A/B Testing at WQU
- Objective: Assess if email campaigns can increase enrollment.
- Methods: Chi-square test, custom ETL pipeline, interactive data app.
- Skills Highlighted: A/B Testing, ETL, OOP in Python.
-
📈 Volatility Forecasting in India
- Objective: Predict asset volatility using a GARCH time series model.
- Methods: GARCH model, API data retrieval, SQLite storage.
- Skills Highlighted: Financial Modeling, API Development, Data Cleaning.
The WorldQuant Applied Data Science Lab offers a unique blend of theory and practical application, focusing on data science skills that solve industry-relevant problems. Each project has helped me strengthen my foundation in areas like machine learning, data engineering, and advanced analytics.
- Languages: Python
- Data Manipulation: Pandas, NumPy
- Visualization: Matplotlib, Seaborn, Plotly Dash
- Machine Learning: Scikit-learn, Statsmodels, XGBoost
- Databases: MongoDB, SQLite
- Data Retrieval: REST APIs
- Other Tools: Git for version control, Jupyter Notebooks for interactive analysis.
I’m looking forward to deepening my knowledge in specialized areas like NLP, time series forecasting and causal inference post-program, alongside expanding my portfolio with more advanced projects. Keep an eye on this repo for updates.
Thank you for visiting my repository! I’ve worked to make each project’s documentation comprehensive and clear, with explanations of my approach, code structure, and visual insights. Don’t hesitate to reach out if you’d like to connect over data science or discuss potential collaborations.