ANKIT KUMAR SINGH

Data Science Intern

Navodita Infotech •  July 2024 - August 2024•  Remote

• Developed a machine learning model to identify fraudulent credit card transactions. • Preprocessed and normalized the transaction data, handled class imbalance issues, and splited the dataset into training and testing sets. • Developed a comprehensive evaluation framework for the classification algorithm, enabling continuous performance assessment and adjustments; the framework is now utilized by 8 data analysts for ongoing model improvement. • Developed a robust evaluation process for model performance using precision, recall, and F1-score; utilized insights to enhance model training protocols, resulting in improved predictability and reliability for over 1M data points analyzed.

Data Science Virtual Internship

BCG•  April 2024 - April 2024•  Remote

• Implemented customer churn analysis simulation techniques for XYZ Analytics, resulting in a streamlined approach that reduced analysis time by 40 hours per month while maintaining high accuracy in predictions. • Conducted efficient data analysis using Python, including Pandas and NumPy. Employed data visualization techniques for insightful trend interpretation. • Completed the engineering and optimization of a random forest model, achieving an 85 Percent accuracy rate in predicting customer churn and completed a concise executive summary for the Associate Director.