Nikhil Thota

San Jose City, CA ***** • ad3c8h@r.postjobfree.com • +1-669-***-**** • LinkedIn • Github • Medium Experienced Data Analyst with a Master's degree in Data Analytics from San Jose State University, specializing in Machine Learning applications. Proficient in SQL, Python, business intelligence (BI) tools, and applying Machine Learning (ML) techniques to real-time applications in diverse analytics domains. EDUCATION

● MASTER OF SCIENCE IN DATA ANALYTICS, SAN JOSE STATE UNIVERSITY San Jose, CA Jan 2023 - Expected. December 2024

● B.TECH IN COMPUTER SCIENCE AND ENGINEERING, IIIT VADODARA Gandhinagar, India Aug 2015- Sept 2019

TECHNICAL SKILLS

● Databases: MSSQL, PostGreSQL, RDBMS, Neo4j, MongoDB, Redshift, BigQuery, MySQL

● Query languages: R, Python, Advanced SQL, DAX, Hive SQL, Java (Object Oriented Programing Programming), PySpark

● Visualization Tools: Data Studio, Matlplotlib, Plotly, Power BI, Tableau, MicroStrategy, Grow (BI), Powerpoint

● Workflow Tools: Airflow DAGS, DBT Cloud (ETL/ELT), Grow (BI), Hive

● Cloud: AWS suite (S3, AWS glue, Redshift, IAM,QuickSight), GCP (Looker,BigQuery, API, IAM), Azure datafactory

● Math: Descriptive Statistics, Probability, Regression, Optimizations

● Machine Learning: Keras, Tensorflow, Pandas, Numpy, Seaborn, scikit-learn, Requests, git, logs EXPERIENCE

Data Analyst, PRODUCT PHARMEASY DEC 2021 - Jan 2023

● Orchestrated a 4% upswing in revenue by meticulously optimizing product listings accuracy, employing SQL,,NER (NLP), CNNs for data driven rules on Product Catalog and implementing automation through Apache Airflow and SageMaker.

● Pioneered a transformative shift, resulting in a remarkable 40% reduction in ad-hoc requests. Engineered data pipelines, models, and dashboards with proficiency in Airflow, Hive, Presto, Redshift, and MicroStrategy.

● Demonstrated analytical prowess, delivering an impressive 8% boost in user conversion rates. Analyzed real-time data seamlessly using Connectors (API), BigQuery, Google Analytics, DAX, and crafted compelling Power BI visualizations.

● Integrated TensorFlow with Python’s PyMC3 for extensive A/B testing using Bayesian methods, applying Natural Language Processing techniques for user interfaces assessment, enhancing experimentation strategies by 15%. Data Business Analyst Saras Analytics DEC 2020 - Dec 2021

● Following Agile SDLC, Optimized marketing strategies & new UI features, achieving a 10% sales uplift by analyzing customer segments and leveraging SQL, DBT, and Looker for precision targeting across Google ads, Meta Ads, and other omni-channel platforms.

● Optimized BigData data models through Airflow, utilizing tools like DBT Cloud, S3, and Python for ETL/ELT processes, enhancing efficiency and scalability across hive/presto platforms reducing costs by 23%.

● Employed Data Warehousing on BigQuery, Snowflake, and Redshift, reducing data redundancy by an impressive 20% and elevating data transparency and accuracy from 40% to > 95% for various e-commerce clients.

● Spearheaded the development of P/L dashboards for Amazon Sellers, resulting in a 20% cost reduction by integrating factors such as budget, forecasted sales, and COGS, providing key business insights using other KPIs through Compelling Tableau viz. Business Analyst Capillary Technologies Pvt. Ltd JAN 2019 - Dec 2020

● Delivered a 4x ROI as an intern by orchestrating data-driven campaign plans, collaborating cross-functionally with teams such as brand marketing, campaign delivery, finance, and legal, to execute successful campaigns in the retail industry.

● Mitigated fraud transactions by 17% in offline retail environments through the implementation of real-time, data-driven rules

● Leveraged Isolation Forests and One-Class SVM algorithms, resulting in a 30% increase in capturing potential fraud, significantly fortifying the security and integrity of transaction processes.

● Drove a 20% increase in CRM growth by deploying advanced models incorporating RFM, Demand Forecasting, and Market Basket Analysis for customer retention, and cross-sell product analysis through real time campaigns using Ads, and SMS.

● Improved the retention rate by 9%, through data driven loyalty program design, and relevant customer segmentation. PROJECTS

● BART, VTA DATA MODELLING: Employed a suite of tools including MySQL Workbench, Python, DBT, Neo4j, MongoDB, Mongo Atlas, BigQuery, GCP, AWS Glue, Kubernetes, and Flask in a comprehensive data modeling project for SJSU. .Jan 2023 - May 2023

● Urban Audio Classification: Led a team of four in a research project focusing on comparative analysis of urban audio classifiers. Aimed to minimize labeled audio data use. Employed UrbanSound8K and ESC-50 datasets for inference and validation. Compared models: Vision Transformers (ViT), CNN, 2D-CNN + BiGRU, and CNN + LSTM. Achieved state-of-the-art results using Data Augmentation with SpecAugment and various dimensionality reduction techniques. Sept 2023 - Dec 2023

● Polypharmacy effects: Developed advanced ML models using PySpark, TensorFlow, and PyTorch to predict adverse drug interactions and assess altered drug efficacy. Executed extensive EDA on ChChSe-Decagon datasets stored in AWS S3, leveraging Tableau for data visualization and SHAP for model interpretation. Sept 2023 - Dec 2023

Contact this candidate