Motivated Data Science graduate with a Master's degree in Data Science. Strong foundation in machine learning, data mining, and AI, with hands-on experience in developing predictive models. Proficient in Python, SQL, and data analysis tools, with a demonstrated ability to analyze large datasets and generate actionable insights. Passionate about leveraging AI and machine learning to solve real-world challenges, improve decision-making, and optimize strategies.
Overview
3
3
years of professional experience
Work History
Data Analyst
Florida International University
10.2022 - 04.2024
Developed robust machine learning models to detect fraudulent activities within the medical provider sector using data from the Centers for Medicare and Medicaid Services (CMS)
Conducted in-depth analysis to identify patterns in fraudulent claims, including trends in procedure and diagnosis codes, provider behavior, and chronic conditions associated with fraud
Performed advanced feature extraction and normalization techniques to improve model accuracy, including encoding categorical data and optimizing feature selection
Implemented Logistic Regression, Decision Trees, and Random Forest models to detect fraud, achieving high accuracy and interpretability
Optimized model parameters using GridSearchCV
Explored advanced architectures, including Long Short-Term Memory (LSTM) networks and autoencoders, for identifying complex patterns in healthcare data
Leveraged Python (Pandas, NumPy, Scikit-learn, TensorFlow) and Jupyter Notebooks to create visualizations (scatter plots, bar charts, heatmaps) and extract actionable insights from complex healthcare data
Intern as Data Analyst
Grip Sparks Foundation
06.2021 - 12.2021
Conducted in-depth research on emerging trends in machine learning and artificial intelligence, applying new techniques to improve model performance and optimize algorithms for real-time decision-making
Maintained and continuously updated existing machine learning models to reflect changes in customer data and business needs, ensuring models stayed accurate, relevant, and reliable for long-term use
Analyzed large and complex datasets to uncover hidden patterns and trends in customer behavior, using advanced statistical techniques and machine learning algorithms to predict future customer actions and preferences
Implemented data visualization tools and techniques to present key findings from machine learning analyses to non-technical stakeholders, enabling data-driven decision-making across marketing, sales, and customer support teams
Regularly tested and validated machine learning models to ensure robustness and accuracy, using techniques such as cross-validation, hyper parameter tuning, and performance metrics evaluation