Abhinaya Reddy
Data Scientist & Statistical Analyst specializing in advanced analytics, machine learning, and data-driven decision making.
Work Experience
My professional journey in data science and analytics
Research Assistant
San Francisco State University | San Francisco, CA
- Guided simulations in statistical modeling and hypothesis testing using Monte Carlo methods.
- Developed curriculum modules with a focus on experimental design and forecasting methods.
- Developed case-based forecasting exercises in Business Forecasting using time series and ARIMA models.
- Led hands-on simulation labs in Computer Simulation using Monte Carlo and discrete-event modeling techniques.
Data Analyst Intern
Headlines Media Group Of Publications | Hyderabad, India
- The reader behavior and engagement data was analyzed to uncover content trends, leading to a 15% increase in the click through rates of articles through data-driven content optimization.
- Developed real-time dashboards for editorial performance tracking, reducing manual reporting efforts by 40% and enabling faster data-informed decisions.
- Conducted A/B testing on headlines and formats, providing actionable insights that improved the average session duration by 20% and increased reader retention.
Projects
A showcase of my data science and analytics projects
E-Commerce Recommendation using GenAI
Engineered a GenAI-powered e-commerce recommendation system that reduced irrelevant product suggestions by 75% using semantic search, RAG techniques, and dynamic user input processing, enabling highly personalized shopping experiences.
Tools Used:
Python, Streamlit, Langchain, OpenAI API, FAISS, Pandas, Seaborn, Matplotlib
Customer Churn Analysis
Increased churn prediction accuracy by 15% through advanced feature engineering and model optimization, enabling targeted retention strategies. Built and evaluated multiple classification models, translating customer behavior data into actionable business insights.
Tools Used:
Python, Pandas, Scikit-learn, Matplotlib, Seaborn
Supply Chain Optimization with Demand Forecasting
Improved sales forecast accuracy by 20% through a custom Random Forest model, allowing proactive inventory decisions and reducing stock outs. Built a feature-rich forecasting pipeline that captured seasonality, promotions and regional variations - contributing to a data-driven supply chain strategy aligned with business goals.
Tools Used:
Python, Scikit-learn, Pandas, Plotly
Skills & Technologies
Programming Languages
Python (Pandas, NumPy, Matplotlib, Seaborn, Scikit-learn), SQL, R, MongoDB
Data Analysis & Cloud Tools
Power BI (DAX, Power Query), Tableau, AWS (S3, Redshift), Azure (Data Factory, Synapse), Github, Excel, Airflow, Snowflake, Oracle, Open AI
Data-Driven Decision Making
A/B Testing, Regression Analysis, Machine Learning (Classification, Clustering, NLP), Data Modelling, ETL/ELT Pipelines
Soft Skills
Problem-Solving, Critical Thinking, Communication, Collaboration
Education
Master of Science in Statistical Data Science
San Francisco State University | San Francisco, CA
GPA: 3.9/4.0
Duration: Sept 2024 – May 2025
Relevant Coursework:
- Statistical Methods for Data Analysis
- Data Mining
- Machine Learning
- Applied Multivariate Analysis
- Experimental Design and Analysis
- Programming for Data Analysis
- Natural Language Processing
- Deep Learning
Focused on advanced statistical methods and machine learning techniques for data-driven decision making and predictive analytics.
Certifications
Google Professional Data Analytics Certificate
Comprehensive certification covering data analysis techniques, tools, and methodologies used in professional data analytics.
View CertificateDownload My Resume
Want to learn more about my qualifications? Download my complete resume to see my full experience, education, and skills.