Shruti Mallavolu

§ Portfolio Website ï linkedin.com/in/shruti-mallavolu/ # ad3ggh@r.postjobfree.com I +1-413-***-**** Summary

Data Enthusiast with a solid foundation in Machine Learning and Data Analysis, coupled with advanced proficiency in Python and SQL. Known for a proactive approach to continuous learning, my goal is to leverage my diverse skill set to make strategic, data-driven decisions that optimize business metrics.

Technical Skills

Programming languages: Python, R, Java, C++ ; DBMS : MySQL, PostgreSQL, No-SQL ; OS : Linux, Windows Tools and Frameworks: Tableau, Docker, AWS, Spark, Airflow, Kubernetes, VS Code, Eclipse, Google Colab, Jupyter ML/AI: Scikit-learn, TensorFlow, Numpy, Pandas, Matplotlib, Seaborn, Pytorch, AutoML, EconML, Beautiful Soup, Statistics Professional Experience

Microsoft (ALICE team) Feb 2023 – May 2023

Graduate Student Researcher Python, Scikit-learn, JupyterHub, EconML Amherst, MA

• Automated the selection of first-stage models and hyperparameters for CATE estimators used in Causal Inference enhancing user input flexibility while concurrently decreasing Mean Squared Error (MSE) and runtime for improved model efficiency.

• Enhanced R2 score by 6% through advanced feature engineering which includes feature selection through importance scores and strategic model selection, leveraging regression and classification algorithms on semi-synthetic and synthetic datasets.

• Achieved 62% Runtime and 90% Tao Risk improvement by opting Bayesian over Grid Search for hyperparameter optimization.

• Effectively communicated progress through reports and presentations to team and mentors. Salesforce Aug 2021 – Nov 2021

Support Analyst Salesforce Marketing Cloud, SQL Hyderabad, India

• Analyzed and debugged over 7% of incidental data generated from all customer reports within my team to promptly resolve cases.

• Provided support in Email Studios for A/B testing and integrations between Salesforce CRM and Marketing Cloud. Bank of America Jun 2019 – Jul 2021

Software Engineer Salesforce CRM, Sales Cloud, Apex, OOPs, REST API, Bitbucket, Agile, JIRA Chennai, India

• Spearheaded ARM portal enhancement, optimizing logic using Apex Triggers, Batch jobs, SQL queries, and test classes achieving atleast 80% coverage enabling Financial Advisors’ role requests, achieving 50% efficiency boost.

• Implemented a texting interface for streamlined Financial Advisor-Customer communication, integrating Mulesoft and Twilio via REST APIs, reducing response time by 25%.

• Refactored application components, reducing codebase by 1000+ lines and improving system performance by 30%.

• Executed daily jobs on Mulesoft to extract data from multiple external systems to synchronize the Accounts data in Salesforce.

• Configured Hadoop cluster to query Salesforce historical data when limits exceeded and stored results in an on-premise SQL database for enhanced data management.

• Engaged in an Agile SDLC, actively participated in code reviews and monitored production-ready changes in Bitbucket. Projects

Review of Machine Learning algorithms on various datasets Numpy, Pandas, Matplotlib, Google Colab Feb 2022

• Selected challenging datasets and executed supervised learning models - Neural Networks, Random Forests, Decision Trees and K- Nearest Neighbours (K-NN) from scratch in python with an accuracy rate of over 90%.

• Evaluated Machine Learning performance metrics - Accuracy, Precision, Recall, Confusion matrix and F1 score to find optimal algorithm for five datasets (Datasets - Parkinsons, Digits, Titanic, Loan, Telecust). World Development Indicators Dashboard Python, Streamlit, Seaborn Mar 2022

• Designed an interactive dashboard, representing effect of certain indicators on any particular country in the World Map.

• Enhanced the visualizations by scatter plot and bar graph showcasing the effect of each indicator by allowing a dynamic selection of years and indicators. Incorporated a video feature in scatter plot and bar graph showing evolution of trends over the years. Predictive Analysis on Stroke Dataset R, Statistical Analysis, Kaggle Jul 2022

• Analyzed Stroke Prediction Dataset available on Kaggle to predict Body Mass Index using patients’ average glucose level and age.

• Data analysis drawn linear regression model revealed significant correlation among dependent and independent variables with R2 of 0.2839. Results drawn from chi-square depict a weak correlation between gender vs stroke, and residence type vs stroke. Data Analysis and Reporting of College Donations Tableau, Excel May 2023

• Conducted a comprehensive analysis of college gifts, leveraging Tableau and Excel, to provide insights into donation patterns.

• Visualized and identified key academic donor trends, top college types, historical patterns, and peak donation years. Build a Toy Store using Microservices Docker, Kubernetes, AWS, gRPC Apr 2022

• Deployed 3 distributed microservices - Front-end Service accepts client request, Order Service stores order details and Catalog Service stores toy details. Programmed system to accept concurrent requests, built multi-threading, caching, and fault tolerance. Education

University of Massachusetts Amherst Jan 2022 - Dec 2023 Master of Science in Computer Science (Concentration in Data Science), GPA: 3.9/4.0 Amherst, MA

• Coursework: ML, Statistics, Information Retrieval, Reinforcement Learning, Data Science Algorithms, Distributed Systems SRM Institute of Science and Technology Jun 2015 – May 2019 Bachelor of Technology in Computer Science, GPA: 8.67/10.0 Chennai, India

• Coursework: Data Structures and Algorithms, Database Systems, Natural Language Processing, Data Mining, AI

Contact this candidate