With a Master’s in Applied Data Science & AI, I bring expertise in prediction modeling, classification, clustering, and text analysis. My skill set includes data scraping, preprocessing and feature engineering, model validation, cross‑validation, and hyperparameter tuning. I work fluently in R, Python, and cloud platforms like AWS to build, optimize, and deploy data‑driven solutions.

I use statistical modeling and machine learning to forecast key business outcomes, from operational demand to client churn risk. These predictive models turn historical data into forward‑looking insights, allowing teams to anticipate challenges and act before issues arise.

​

Skills & Models:

• Time series forecasting (ARIMA)

• Regression Modeling (Linear, Logistic, Ridge, Lasso)

• Ensemble Methods (Random Forest, Gradient Boosted Trees, XGBoost)

I design and train machine learning models to categorize data into meaningful groups, enabling faster decision‑making and more efficient workflows. From identifying high‑value clients to routing service requests, classification models help turn raw inputs into structured, actionable information.

​

Skills & Models

• Model Evaluation (Precision, Recall, F1-score, ROC-AUC)

• Handling imbalanced datasets (SMOTE, class weighting)

• Logistic Regression, Decision Trees, Random Forest

• Gradient Boosting (XGBoost, LightGBM), CatBoost)

• Support Vector Machines (SVM)

• Naive Bayes, K-Nearest Neighbors, Neural Networks

I apply natural language processing (NLP) techniques to extract insights, identify patterns, and derive meaning from unstructured text data. From customer feedback and survey results to RFPs and contracts, text analysis turns qualitative information into measurable, actionable intelligence.

​

Skills & Models

• Text cleaning, tokenization, and preprocessing

• Sentiment analysis and opinion mining

• Topic modeling for thematic discovery (LDA)

• Keyword extraction and frequency analysis