Data Scientist Analyst

Vivekananda Reddy Thummala

San Jose, CA

510-***-**** # ***************@*****.*** ï linkedin.com/in/vivekananda-reddy-thummala § github.com/tvivekanandareddy Education

California State University,Eastbay Aug. 2022 – Dec 2024 MS in Statistics, Data Science Hayward, CA

Certification

Python, SQL, Informatica(MDM Saas, IDMC, CDGC), Excel, Tableau, Gen AI Prompt Engineering Experience

ISoftech Inc June 2024 – Present

Data Scientist (Remote) Chantilly, VA

• Optimized recommendation algorithms using matrix factorization and linear algebra techniques, improving recommendation relevance scores by 18%.

• Applied adv statistical methods, such as hypothesis testing and ANOVA, to evaluate A/B test results, reducing error rate by 25%.

• Conducted Exploratory Data Analysis (EDA) on multi-million-row datasets to identify customer behavior trends, driving a 15% increase in retention.

• Automated data preprocessing pipelines using Python and SQL, reducing manual data cleaning efforts by 40%.

• Visualized data insights using Tableau and matplotlib, enabling stakeholders to make informed decisions. Cynnent Systems Pvt Ltd July 2021 – July 2022

Data Analyst (Remote) Bengaluru, India

• Created advanced Tableau dashboards, integrating AWS, Snowflake, and Google marketing data, leading to a 5% revenue increase.

• Optimized ETL processes with ADF, Databricks, Synapse, boosting throughput by 15% and ensuring efficient data flow.

• Utilized SARIMA, VAR, and Prophet models to forecast sales trends, improving prediction accuracy by 15%.

• Engineered a routing tool with Google Postman, achieving a 20% reduction in processing time and elevated operational efficiency.

• Implemented rigorous testing strategies, achieving enhanced data accuracy and a notable 15% increase in user experience metrics. Neyveli Lignite Corporation (NLC) Thermal Plant Mar. 2021 – Apr. 2021 Internship Tamil Nadu, India

• Applied clustering and classification techniques to NLC data, achieving 85% precision in forecasting water pollution timelines.

• Identified crucial pollution hotspots and projected timelines, enhancing targeted environmental management by 20%. Indian Space Research Organization (ISRO) Nov. 2019 – Dec 2019 Internship Andhra Pradesh, India

• Developed visualization tools in R for wind pattern data, enhancing forecasting by 10%.

• Executed robust data collection via R, driving key operational insights and achieving a 15% increase in launch safety metrics. Bharat Sanchar Nigam Limited (BSNL) May 2019 – June 2019 Internship Andhra Pradesh, India

• Implemented data preprocessing and EDA through pandas to reveal pivotal sales drivers, resulting in a 30% uplift in yearly sales.

• Conducted intricate EDA using pandas and matplotlib, generating key sales insights validated by K-fold cross-validation. Projects

Equity Research Tool – AI-Powered Information Extraction & Retrieval Python, Langchain, Vector DB, RAG

• Built an AI tool with Python, Streamlit, LangChain, and FAISS to extract insights from unstructured URLs.

• Used RecursiveTextSplitter, OpenAI embeddings, and FAISS Vector DB for content processing and retrieval.

• Integrated RetrievalQAWithSourceChain and a Streamlit frontend for interactive financial research. Disfluency detection in public speaking using Deep Learning Python, Deep learning

• Applied Transformer-based models (BERT, GPT-based models) to improve speech disfluency detection.

• Integrated Google Cloud Speech-to-Text API for real-time speech processing and transcription.

• Optimized model inference using Vertex AI, reducing latency by 15% for real-time speech analysis. Technical Skills

Programming Language: Python, SQL, R, Git, LaTeX, HTML, VS Code Generative AI & NLP: LLMs (GPT, BERT), Vertex AI, Dialogflow CX, Prompt Engineering, RAG Technologies: Machine Learning, Deep Learning, Time Series Analysis Frameworks: LangChain,Tensorflow, Pytorch, dplyr, ggplot, tidyverse Big Data & Cloud Technologies: Google Cloud Functions, BigQuery, Looker Studio, AWS, Azure, Snowflake Databases & Tools: MySQL, NoSQL, Power BI, Tableau Soft Skills: Time Management, Problem-solving, Documentation, Engaging Presentation, Leadership Publication

3D CNN Based Emotion Recognition Using Facial Gestures

• Teja, K.S.S., Reddy, T.V., Sashank, M., Revathi, A., ”3D CNN Based Emotion Recognition Using Facial Gestures,” 9th International Conference on Frontiers in Intelligent Computing: Theory and Applications, Springer, vol 267, pp. 319-325, June, 2021 Link

Contact this candidate