Welcome to my GitHub profile! I'm passionate about using data science to solve complex problems and make data-driven decisions. My academic background in statistics and management & data science has equipped me with a strong foundation in machine learning, statistical analysis, and data visualization. Here, you'll find projects showcasing my skills in Python and various machine learning techniques.

• Data Analysis: Proficient in cleaning, transforming, and performing exploratory analysis to extract meaningful information from datasets.
• Feature Engineering: Strong background in creating creative and predictive features to improve performance of machine learning models.
• Machine Learning: Expertise in applying various algorithms and models including boosting, bagging, recommender systems, and deep learning.
• Natural Language Processing (NLP): Experienced in utilizing NLP techniques for text data processing, analysis, and deriving insights.
• Data Visualization: Skilled in using libraries such as Matplotlib and Seaborn for creating and presenting visualzations to stakeholders.
• Statistical Analysis: Strong foundation in statistical methods to uncover patterns, validate hypotheses, and derive actionable insights from data.

• Python: Advanced proficiency in Python, leveraging libraries like Pandas, NumPy, and scikit-learn for efficient data analysis and machine learning workflows.
• R: Competent in using R for statistical analysis and data visualization, utilizing packages like dplyr and ggplot2.
• SQL: Comfortable with SQL for querying and manipulating databases to support data analysis tasks.
• SAS: Knowledgeable in SAS for data manipulation, statistical modeling, and analysis.
• Tools: Jupyter Notebook, Tableau, Git, VS Code, R Studio

• Recommender-System-LightGBM: Developed a personalized fashion product recommender system using LightGBM and compared results to baseline and UUCF. Extensive feature engineering using nlp, SVD, cosine similarity, and more.

  • Topics:

• FinCrime-Fraud-Detection: Created models leveraging machine learning to mitigate fraud and credit risk in financial transactions. Creative and effective feature engineering performed using domain knowledge.

  • Topics:

• Political-Bias-Detection: Employed transformers for implementing a pre-trained hugging face model for political lean prediction. Analysed reading behaviors based on user location.

  • Topics:

• Market-Basket-Analysis: Analyzed transaction data to uncover purchasing patterns using Apriori and FP-Growth algorithms.

  • Topics:

Data Engineering Skills!
Tools: Docker, Terraform, Airflow, BigQuery, dbt