About
Highly analytical Data Scientist with strong expertise in statistical analysis, data visualization, and predictive modeling, proficient in Python and SQL. Adept at data mining, wrangling, and transforming complex datasets into accurate, actionable insights. Committed to delivering high-quality, results-driven solutions that enhance business operations and strategic decision-making.
Work
Faridabad, Haryana, India
→
Summary
Conducted in-depth credit risk analysis on a complex dataset, identifying key patterns and correlations to enhance predictive modeling for loan defaults.
Highlights
Managed a complex dataset by effectively addressing missing values, dropping over 50% of sparse columns, and accurately imputing numerical and categorical data using median and mode methods.
Identified and mitigated outliers within the dataset using the Interquartile Range (IQR) method, significantly enhancing data quality and ensuring the reliability of subsequent analyses.
Performed comprehensive univariate and bivariate analysis utilizing advanced Python libraries (Pandas, NumPy, Matplotlib, Seaborn) to uncover critical patterns in loan default risk.
Analyzed intricate correlations between key features such as 'DAYS_BIRTH' and 'EXIT_SOURCE_3' and the target variable, providing actionable insights crucial for robust risk assessment and strategic decision-making.
Faridabad, Haryana, India
→
Summary
Developed a Python-based e-commerce data management system to streamline product information handling and enhance data accessibility for business operations.
Highlights
Developed a comprehensive Python-based e-commerce data management system, efficiently handling product information across CSV, JSON, and TXT file formats to significantly enhance data organization and accessibility.
Implemented robust file handling functions utilizing `os`, `csv`, and `json` modules to seamlessly load, modify, and save diverse product sales data, details, and descriptions, ensuring high data processing efficiency.
Designed and integrated rigorous input validation mechanisms for SKUs (13-character length) and sales data (14 integers), substantially improving data integrity and optimizing user experience in administrative tasks.
Created modular functions (e.g., `load_data`, `update`, `dump_data`) to streamline data operations, enabling fluid addition and updating of product information with intuitive, user-friendly prompts.
Skills
Programming Languages
Python, SQL.
Tools & Libraries
Pandas, NumPy, Matplotlib, Seaborn, os, csv, json, Microsoft Word.
Soft Skills
Communication Skills, Detail-Oriented, Problem-Solving, Analytical Thinking.
Data Analytics
Data Collection, Data Analysis, Data Mining, Data Wrangling, Predictive Modeling, Statistical Analysis, Data Visualization, Data Management, Data Cleaning.
Support
Ticket Tools, MDM Management, AD Migration.