Sai Krishna Vamsy Alapati

Atlanta, GA 404-***-**** adt9mj@r.postjobfree.com LinkedIn

EDUCATION

Georgia State University, J. Mack Robinson College of Business (GPA: 4.15) Atlanta, GA Master of Science in Information Systems (Major: Big Data Management and Analytics) July 2023 Vellore Institute of Technology (GPA: 8.51) Vellore, IN Bachelor of Technology (Major: Electronics and Communication Engineering) May 2019 SKILLS

Analytics : NumPy, Pandas, Matplotlib, Seaborn, Scikit-learn, TensorFlow, H2O, Keras ML Techniques : Classification, Prediction, Regression, Clustering, EDA, Visualizations, ETL/ELT Pipelines, Cross Validation, Deep Learning, RNN, CNN, NLP Big Data : PySpark, Spark, Hadoop, BigQuery

Database : Oracle SQL, Oracle PL/SQL, MySQL

Programming : Python, R, C, Pro*C, GIT, Oracle Forms (11g/12c), Shell, JavaScript Developer Tools : Databricks, Jupyter Notebooks, Google Colab, PyCharm, R-Studio, VSCode, Tableau Other Tools : AWS, Gitlab, GitHub, JIRA, Confluence, Autosys, Jenkins Certifications : Version Control with GIT, SQL(Basic), SQL(Intermediate) PROFESSIONAL EXPERIENCE

GEORGIA STATE UNIVERSITY Atlanta, GA

Graduate Research Assistant (Mentor: Dr. Mark Keil – John B. Zellars Professor of CIS) August 2022 - Present

• Assisted in conducting a class of 30 students, teaching, along with research work in IT risk management. EMPOWER RETIREMENT Bangalore, India

Developer Software June 2019 - July 2022

• Led a team of 6 and redesigned the payroll reports to improve efficiency by ~40% and readability while introducing the option of customizing the reports to the business users.

• Co-designed and implemented an end-to-end payroll file load process using Pro*C and PL/SQL enhancing the flexibility of the framework to process a file containing contributions from multiple clients at once.

• Migrated the Pro*C code to Java API to facilitate integration to front-end React pages achieving over 90% code coverage.

• Developed and maintained a payroll file configuration web app in React JS with over ~1000 users in the operations team.

• Designed, Developed, tested and supported applications in a 10-member team, working in an Agile Environment. PROJECTS

Media Promotion Cost Prediction (PySpark, Python, Pandas, Databricks, Google Colab, Tableau, ETL Pipeline)

• Extracted, cleaned and tidied the dataset and performed exploratory data analysis using seaborn and tableau to aid in the feature selection. Used Ordinal encoding to encode the categorical columns. Using ETL/ELT pipelines to develop ML models such as Random Forest Regressor, Decision Tree Regressor, KNN Regressor etc. with cross-validation 5 folds to predict the cost of promoting a product of a convenience store in USA with high R2 score (0.9984) and low RMSE (1.1862). ETA of a Response on Stack Overflow (R, Stack Exchange API, Feature Engineering, Deep Learning, AI, ML, EDA)

• Collected the data of questions posted on the stack overflow website using the Stack Exchange public API. Extracted the dataset from the JSON API response of API. Cleaned and performed EDA to understand the story the data is telling. Featured engineered to create new columns using the existing data. Used Deep Learning with hyper-parameters and AUTOML modules in H2O to train and create models. AUTOML model achieved and R2 score of 0.9129 and RMSE of 142.9427. German Customer Credit-Worthiness Prediction (R, R-Studio, ML, EDA)

• Modelled classification models as Logistic, KNN, Random Forest, Neural Networks, Decision Tree algorithms with Min-Max scaling the data and Ensemble using averaging in order to classify a customer as credit-worthy or not based on the data of the German subjects and achieved an accuracy of 80% and acceptable F1 Score. AWARDS, RECOGNITION AND LEADERSHIP

• Recognition: Best Team of Quarter 2019, Empower Rising Star 2020, Empower MVP Award 2022, Empower

• Assistant Manager for Tech and Cultural Fests, VIT, 2018 hosting an audience of 25000. Member/Tutor at NGO RotaractVIT