Dhruv Gangwani

● Led end-to-end project phases, including Planning, Data Collection, Model Development, Training, Evaluation, and Deployment in AWS.
● Spearheaded a comprehensive machine learning project to predict insurance costs, leveraging extensive datasets encompassing policyholder information, claims data, and external variables.
● Demonstrated a keen understanding of feature engineering, identifying and incorporating critical variables to enhance model accuracy and predictive capabilities.
● Led a comprehensive brand monitoring initiative, leveraging advanced tools to systematically extract public opinions about our product from diverse online platforms.
● Implemented state-of-the-art NLP Aspect-based sentiment analysis techniques, providing a nuanced understanding of customer sentiments and identifying key trends in brand perception.
● Developed and executed strategies for real-time monitoring of social media channels, resulting in immediate identification and response to emerging trends and NLP sentiments related to the product.
● Employed analytical programming languages like R, Python, and MATLAB.
● Developed machine learning algorithms using Python libraries like pandas, numpy, seaborn, scipy,
matplotlib, and scikit-learn.
● Extracted data from HDFS, performed data munging for exploratory analysis and created machine-learning
models on large-scale text data.
● Collaborated with the Business Intelligence team using Tableau for reporting and data visualization.
● Managed large datasets using statistical tools and techniques, and integrated machine learning solutions
with the data engineering team.
● Worked on big data projects using PySpark and implemented machine learning with ML and MLlib
packages.
● Performed data profiling, defined source-to-target data mappings, and applied ETL tools like Talend and
Informatica PowerCenter.
● Utilized Informatica tools for legacy data analysis and data profiling.
● Deployed models on AWS EC2 and EMR, storing them in AWS S3.
● Extracted source data from various databases like Oracle, MS SQL Server, and Excel.
● Developed and maintained a Data Dictionary for metadata reporting.
● Performed predictive modeling using state-of-the-art methods and maintained dashboards and reporting
systems.
● Parsed and manipulated raw data streams for analytical tools.
● Built sustainable and trustful relationships with senior leaders.
● Worked with a wide range of technologies, including Teradata, PL/SQL, SPSS, SQL Server, Oracle, SSAS,
Infor

Led end-to-end project phases, including Planning, Data Collection, Model Development, Training, Evaluation, and Deployment in AWS.
Spearheaded a comprehensive machine learning project to predict insurance costs, leveraging extensive datasets encompassing policyholder information, claims data, and external variables.
Demonstrated a keen understanding of feature engineering, identifying and incorporating critical variables to enhance model accuracy and predictive capabilities.
Led a comprehensive brand monitoring initiative, leveraging advanced tools to systematically extract public opinions about our product from diverse online platforms.
Implemented state-of-the-art NLP Aspect-based sentiment analysis techniques, providing a nuanced understanding of customer sentiments and identifying key trends in brand perception.
Developed and executed strategies for real-time monitoring of social media channels, resulting in immediate identification and response to emerging trends and NLP sentiments related to the product.
Employed analytical programming languages like R, Python, and MATLAB.
Developed machine learning algorithms using Python libraries like pandas, numpy, seaborn, scipy, matplotlib, and scikit-learn.
Extracted data from HDFS, performed data munging for exploratory analysis and created machine-learning models on large-scale text data.
Collaborated with the Business Intelligence team using Tableau for reporting and data visualization.
Managed large datasets using statistical tools and techniques, and integrated machine learning solutions with the data engineering team.
Worked on big data projects using PySpark and implemented machine learning with ML and MLlib packages.
Performed data profiling, defined source-to-target data mappings, and applied ETL tools like Talend and Informatica PowerCenter.
Utilized Informatica tools for legacy data analysis and data profiling.
Deployed models on AWS EC2 and EMR, storing them in AWS S3.
Extracted source data from various databases like Oracle, MS SQL Server, and Excel.
Developed and maintained a Data Dictionary for metadata reporting.
Performed predictive modeling using state-of-the-art methods and maintained dashboards and reporting systems.
Parsed and manipulated raw data streams for analytical tools.
Built sustainable and trustful relationships with senior leaders.
Worked with a wide range of technologies, including Teradata, PL/SQL, SPSS, SQL Server, Oracle, SSAS, Informatica Power Center, MySQL, Cassandra, Netezza, Linux, Tableau, Microsoft Azure, Google Cloud Platform, and AWS ML.

Developed an AI-powered Alzheimer’s medical test evaluation system with a 96% accuracy using NLP, Deep learning, Image processing, and computer vision, deployed on AWS Serverless architecture using AWS lambda, ECS, and ECR.
Developed Document Information Extraction, a custom Spacy NER solution for extracting business entities from 1000+ invoice variants, utilizing MySQL for data storage, and deploying a web service with Flask API, Gunicorn, and NGINX.
Worked on TensorFlow, Keras, NumPy, Scikit-Learn, Ft. Data API, and Jupyter Notebook, in Python at various stages for developing, maintaining, and optimizing machine learning models.
Developed Scala scripts, UDF’s using both data frames/SQL and RDD in Spark for data aggregation,queries, and writing back into S3 bucket.
Developed Map Reduce/ Spark modules for machine learning & predictive analytics in Hadoop on AWS.
Applied various Classification models such as Na¨ıve Bayes, Logistic Regression, Random Forests, and Support Vector Classifiers, from scikit-learn library and improved performance of the model by using various Ensemble learning like Random Forests, Xgboost and Gradient Boosting using Scikit-learn.
Worked with Spark, Hadoop, HBase, Cassandra, MongoDB, Kafka, Spark Streaming, MLLib, Python, and a wide range of machine learning algorithms such as classifications, regressions, and dimensionality reduction.
Extensive use of Spark Data Frames, Spark-SQL, and Spark MLLib, as well as constructing and designing proof-of-concepts using the Spark SQL and MLlib libraries.
Participated in all steps of data mining, including data gathering, data cleaning, model development, and validation, visualization, and gap analysis. Created a Python tool that utilized numerous libraries (Scipy, Numpy, Pandas) to do classification using supervised methods such as Logistic Regression, Decision Trees, KNN, and Naive Bayes.
Worked on Snowflake Schemas and Data Warehousing and processed batch and streaming data load pipeline using Snow Pipe and Matillion from data lake Confidential AWS S3 bucket.
Leverage Python language fundamentals and syntax to design, develop, and maintain robust data-centric software applications, enhancing business decision-making and operational efficiency.
Implement functionalities using relevant Python libraries and frameworks, such as NumPy, pandas, and Django, aligning with project specifications and enhancing the capabilities of data-driven applications.
Designed and developed interactive dashboards and reports in Power BI to provide key insights, supporting business decision-making.
Utilized DAX queries in Power BI for effective data manipulation, thereby generating custom metrics for more accurate analysis.
Trained end-users on Power BI tool usage, promoting a data-driven culture and increasing user self-service capabilities.
Handle file I/O operations, reading and writing data from various sources efficiently and securely. Perform data cleaning, feature scaling, and engineering using pandas and NumPy packages to ensure high-quality data analysis.
Collaborate with the Analysis & Marketing Team to drive data-informed business decisions, leveraging deep insights from comprehensive data analysis.
Debug and troubleshoot Python code to identify and resolve software issues, ensuring smooth functionality and optimal performance of data analytics tools and applications.
Implement error handling and exception handling techniques to manage unexpected scenarios, providing informative error messages to facilitate easy issue diagnosis and resolution.
Utilize testing frameworks such as unittest or pytest to write unit tests, verifying the reliability and correctness of the developed code and ensuring the robustness of data applications.
Apply test-driven development (TDD) principles to build and maintain high-quality software applications, contributing to improved system reliability and efficiency.
Lead requirement gathering efforts, create business requirement documents, and develop mappings for requirements to generate insightful reports for stakeholders, aiding in the decision-making process.
Conduct advanced data analysis and statistical modeling to predict operational outputs, identify inefficiencies, compare them with historical data, and propose resolutions to enhance business performance.
Design and implement efficient database systems to manage daily operations records, financial documents, and vendor payments, using data modeling, SQL, and database administration skills. Utilize PowerBI for comprehensive data visualization.
Collaborate with cross-functional teams to develop and deliver ad-hoc and standardized reports, delivering valuable metrics to stakeholders at various organizational levels, leveraging strong skills in data analysis, visualization, and communication.
Analyze and visualize daily operational data, compare it with historical trends, and implement solutions to enhance business efficiency and profitability.
Implement industry-standard safety and quality management systems within the organization, ensuring regulatory compliance and high operational standards.
Successfully meet company deadlines for projects by employing data mining, data analysis, and goal-setting techniques, contributing to achieving business objectives and targets.