Prathyusha Buduru
Professional Summary
Data Analyst with 2+ years of experience delivering analytics, ETL, and ML solutions using SQL, Python, Power BI, Azure Databricks, and Snowflake. I design and maintain production ETL pipelines and analysis-ready datasets, having cleaned and validated 50K+ records and automated recurring reporting workflows. I build interactive Power BI dashboards and tabular models to deliver KPIs and decision support to leadership and cross-functional stakeholders. I implement predictive models and NLP pipelines using scikit-learn, PyTorch, and Hugging Face Transformers, and developed a retrieval-augmented generation (RAG) proof-of-concept for document QA. I optimize SQL performance and data models across cloud platforms to improve report reliability. I document validation rules and mentor junior analysts while working in Agile teams to translate business requirements into operational analytics and measurable improvements. Comfortable communicating results to technical and non-technical audiences.
Technical Skills
Work Experience
- Cleaned, validated, and maintained 50K+ record operational datasets using SQL and Python (Pandas), reducing reporting errors and inconsistencies by 20–40% across teams.
- Automated ETL and report-preprocessing workflows in Azure Databricks using Python, eliminating repetitive manual steps and accelerating report readiness.
- Built interactive Power BI dashboards and tabular data models to surface executive KPIs and operational indicators for leadership and business stakeholders.
- Optimized SQL queries and implemented indexing and partitioning strategies in Snowflake and Oracle to improve report refresh performance and query reliability.
- Designed predictive-analysis workflows using Python and scikit-learn to identify operational trends and prioritize process improvements.
- Reconciled and standardized data across Snowflake, Oracle, and Azure SQL source systems using deterministic matching and validation rules to improve downstream report stability.
- Created technical documentation and validation checks describing ETL logic, data definitions, and recurring reporting workflows to enable maintenance and handover.
- Mentored junior analysts on SQL query design and Power BI report-building best practices and coordinated analytical tasks within Agile sprints.
- Completed applied training covering Python, statistics, feature engineering, model evaluation, and end-to-end ML workflows.
- Built a hate-speech detection classifier by preprocessing text, applying CountVectorizer features, and training a Decision Tree model; evaluated performance with accuracy and confusion-matrix analysis.
- Developed a spam SMS classifier using text preprocessing and oversampling to address class imbalance and improve minority-class recall.
- Implemented end-to-end ML pipelines including exploratory data analysis, feature engineering, model training, and validation using scikit-learn.
- Visualized data distributions and model performance with Matplotlib and Pandas to inform feature-selection and preprocessing decisions.
- Documented model pipelines and experimental results in notebooks for reproducibility and peer review.
Projects
- Built a Multi-Layer Perceptron in PyTorch to predict customer churn from tabular data with 30 input features and progressively smaller hidden layers.
- Implemented batch normalization and Xavier initialization and benchmarked Adam vs. SGD optimizers to compare convergence behavior.
- Applied dropout regularization and measured its effect on validation stability and generalization compared to a baseline model.
- Connected predictive outputs to retention strategies for targeted engagement and personalized offers.
- Designed an interactive Power BI dashboard analyzing relationships between household income and housing affordability across metros and micro areas.
- Integrated multiple ACS datasets into a unified analytical model and created KPI cards, maps, and cross-filtering visuals.
- Analyzed housing cost burden defined as households spending >30% of income on housing and surfaced regional affordability trends.
- Built an end-to-end Retrieval-Augmented Generation pipeline for question answering over academic policy documents.
- Implemented PDF ingestion and text chunking, generated sentence embeddings with Sentence-Transformers, and implemented cosine-similarity retrieval.
- Integrated a lightweight LLM to generate grounded responses from retrieved context and compared RAG responses against LLM-only outputs.
- Fine-tuned bert-base-uncased on 15,000 comments to classify toxic content and addressed a 90/10 class imbalance with sampling strategies.
- Trained using AdamW and learning-rate scheduling, achieving a strong minority-class F1 and improved recall versus a logistic-regression baseline.
- Translated model outputs into a scalable content-moderation workflow with evaluation metrics and deployment considerations.
- Built and compared RNN, LSTM, and GRU architectures on 12,334 historical stock-price records using sequence windows and train/validation/test splits.
- Configured two-layer recurrent models with dropout and Adam optimization and evaluated predictions using RMSE to compare architectures.
- Documented performance trade-offs and used results to recommend architectures for short-horizon forecasting.
- Built a custom CNN and fine-tuned ResNet-18 to classify tomato-leaf diseases, applying standard image preprocessing and augmentation.
- Trained models with CrossEntropyLoss and Adam optimizer and compared validation accuracy and per-class precision/recall.
- Deployed an interactive Gradio app for image upload, inference, and confidence reporting to demonstrate usability.
- Analyzed 50,000+ e-commerce transactions using SQL to derive revenue trends, product rankings, and customer RFM segments.
- Applied window functions (RANK, LAG, SUM() OVER()) and chained CTEs to compute month-over-month growth and cumulative revenue metrics.
- Segmented customers into high-value, at-risk, and one-time buyers to inform targeted marketing strategies.
- Designed and analyzed an A/B experiment comparing checkout-flow variants, defining conversion rate as the primary metric and guardrails for business impact.
- Calculated minimum sample size via power analysis and executed two-proportion z-tests with confidence intervals and effect-size interpretation.
- Documented statistical significance versus business significance and recommended follow-up testing strategies.
- Created monthly customer cohorts based on first-purchase date and measured repeat-purchase retention across subsequent periods using Pandas.
- Built cohort-retention matrices and visualized retention with annotated Seaborn heatmaps; reimplemented analysis in Power BI using DAX measures.
- Developed a Power Query pipeline to transform inconsistent government open data into an analysis-ready dataset, resolving date and categorical inconsistencies.
- Implemented fuzzy matching and validation checks for duplicates, reference totals, and refresh-time quality to ensure dataset reliability.
- Delivered a multi-page Power BI dashboard with data-quality documentation and remediation recommendations.
- Built an interactive Tableau dashboard tracking year-over-year revenue, profit margin, and category performance with parameter controls and exponential-smoothing forecasts.
- Created KPI summary cards, drill-down tables, and contextual tooltips to enable manager-level decision making.
- Conducted an analytical study evaluating retail expansion opportunities by integrating store performance with public demographic and economic indicators using SQL and Python.
- Engineered metrics such as sales per capita and built a weighted opportunity-scoring framework; delivered findings via Power BI dashboards and an executive summary.
Education
Certifications
Powered by Drivetube · Create your own profile at drivetube.ai
Everything on Drivetube
Six products, two of them free forever. Start wherever you are.
Your free digital resume
at drivetube.ai/in/your-name: one true standard resume with a Hiring Snapshot (visa status, expected salary, notice period, work preference, relocation), an ATS-ready PDF download and a single shareable link. Free forever; interview requests come from verified employers and your contact details stay masked until you accept.
Documentation- Free Job BoardFree
Verified jobs, posted in the last 3 days
verified openings crawled ATS-by-ATS from 160,000+ real company career pages across 50+ ATS platforms. Shows the true posting date from the source ATS — not when a listing was indexed — and deletes every general listing 3 days after it was actually posted. No ghost jobs, no ad-sponsored listings, no staffing reposts, no account needed.
Documentation - Resume Writing ServicesFrom $25.99
Written by senior career writers
human-written, ATS-optimised resumes by senior career writers, from ₹499.99 / $25.99. Available in every country, written to the destination country's own standard — a US resume, UK CV, German Lebenslauf and Indian resume are genuinely different documents. A paid service, separate from the free Drivetube Profile.
Documentation - Drivetube OneFrom $39.99 / 3 mo
Daily matched jobs, tailored resumes, or we apply for you
Drivetube's paid service. Community sends daily Jobsheets of fresh jobs matched to your profile on WhatsApp and email, with the Drivetube Community ($39.99 for 3 months or $69.99 for 6 months; ₹999 or ₹1,899 in India). Jobhunt is one-time application credits with Community included: one credit tailors one resume and its cover letter (100 for $99 with 3 months of Community, 250 for $199 with 6 months). Let Us Apply is an add-on to Jobhunt: a human expert applies 250 times for you on your credits ($0.60 each, $150). Everything lives on one dashboard at drivetube.ai/drivetubeone.
Documentation - Drivetube HireFree tier
For employers — no job postings, no applications
hiring with no job postings and no applications. Paste your real job description and AI matches it against candidates' true standard resumes, returning ranked candidates with a match %, matched and missing skills and written reasoning. Free tier included; employers pay, candidates never do.
Documentation
- Documentation
every product explained in full, with feature-by-feature comparisons against the job boards, AI apply tools, resume services and hiring platforms people actually use.
- Playbooks
tactical job-search guides. Each post is one named tactic with the situation it applies to, the exact steps, a copy-paste message and honest failure modes. Free, no account.
The job board covers the United States, India, United Kingdom, Canada, Europe and Australia, and Resume Writing Services are available in every country.
Pricing is identical on the web, iOS and Android — no app-store markup. Monthly Community membership is purchased in the iOS app only; the website sells annual plans. The Android app has no in-app purchase, so Android members subscribe on drivetube.ai and then sign in to the app with full access. Membership follows your account, not your device.