Amruta Shah

Assist in collecting, cleaning, and organizing large datasets from various sources using pyspark and python. Employed statistical tech. & powerful visualization tools to conduct data analysis, identifying patterns, trends, and insights. Developed and implemented machine learning models for predictive analytics and decision-making. Work with structured & unstructured data to extract relevant features and perform 70% data transformations using pyspark, MySQL and python. Collaborated with cross-functional teams to understand business requirements and develop data-driven solutions. Participated in the design, development, and deployment of machine learning systems.

Collaborated with customers to fulfill 100% of their requirements and preferences. Created 100% comprehensive techno-commercial proposals for PLC, SCADA, HMI, and Electrical projects. Designed Control System Hardware/Software in detail, ensuring 100% functionality. Conceived and adhered to 100% project budget constraints, meeting design targets within cost standards. Supervised installation, testing, and pre-commissioning activities of PLC, SCADA, HMI, and control panels with a 100% success rate. Prioritized all engineering work to ensure timely completion of projects. Successfully completed all projects independently, with a 100% on-time delivery record. Implemented cost-reducing strategies and improved efficiency of engineering team. Conducted comprehensive analysis of employee performance data using Python and MySQL. Developed data models and schemas in MySQL to organize and store employee performance data efficiently. Utilized Python programming and data analysis libraries (e.g., Pandas, Matplotlib) to extract insights and identify patterns, supporting data-driven decision-making. Developed a predictive model on AWS cloud using machine learning techniques to identify potential microcredit loan defaulters. Experienced in all aspects of data handling, including mining, cleaning, and manipulation, using renowned tools such as Pandas and NumPy. Conducted data preprocessing, feature engineering, and exploratory data analysis to gain insights into the loan dataset. Utilized logistic regression, random forest, and gradient boosting algorithms to build the predictive model.

Understand analytics & modeling needs and build validated data pipelines to extract data, build new predictive features to build 100% ML models. Extracted usable data by performing web scraping using Selenium and Beautiful Soup from valuable data sources. Researched and implemented data pre-processing techniques for both structured and unstructured big data, resulting in a 95% improvement in data quality in pyspark & python. Ensured 100% data integrity by cleansing and validating big data sets for analysis using pyspark or python. Analyzed large volumes of information, identifying patterns and delivering solutions. Engineered exploratory data analysis (EDA) to extract insights and develop effective solutions, resulting in a 90% improvement in decision-making accuracy. Developed and implement 80% feature engineering strategies to extract meaningful features from raw data and optimize model performance. Implemented, constructed and optimized predictive models using various ML algorithms achieving a 90% prediction accuracy. Construct and maintain scalable data processing systems to support data science workflows. Presented and documented results in clear reports, providing stakeholders with a 100% understanding of key insights. Revamped data visualization techniques, effectively communicating key metrics and insights to stakeholders and resulting in a 95% improvement in data comprehension.