DataStory Logo
DataStory team

OUR WORK

RECENT PROJECTS

Aflac

Engineered an ETL pipeline that transformed over one million U.S. Department of Labor Form 5500 records into a highly accurate, queryable dataset. Utilized NLP, entity resolution, and automated validation workflows to improve subsidiary mapping and ensure data quality at scale.

Selector

Developed low-latency machine learning pipelines for real-time anomaly detection and automated security data analysis. Optimized data processing and inference workflows to deliver rapid insights across cloud infrastructure and CI/CD environments.

Oracle

Built a multi-agent research platform using LangChain and Oracle AI Database 26ai to analyze financial metrics and live news in parallel. Synthesized insights into strategic briefs, SWOT analyses, and an interactive dashboard to support investment research and decision-making.

DataStory

Built a full-stack sourcing and outreach platform that combined PitchBook data, web scraping, and company enrichment to automate prospect research. Leveraged LLMs to generate personalized outbound email drafts and streamline lead tracking, outreach, and engagement workflows.

PAST PROJECTS

UNICEF

Created web scrapers to identify potential partner organizations for UNICEF by utilizing sentiment analysis on social media posts to target organizations with a higher propensity to join.

EA Games

Developed a web scraper to capture game leak data, integrating it with an ETL pipeline into Snowflake. Enhanced classification accuracy using confusion matrices and initiated predictive analytics on sentiment and revenue trends.

Seagate

Developed a PostgreSQL-integrated priority scoring framework for automating accounts payable and cost modeling. Built Tableau dashboards with drill-down analytics and streamlined ETL workflows using Metabase and Streamlit.

EPRI

Built generative machine learning models including LSTM, GANs, and VAEs to synthesize ultrasonic A-scans for non-destructive testing.

The Education Trust

Constructed an ETL Snowflake pipeline to automate collection and data. Generated multiple Tableau visualizations using piped data.

The Farmlink Project

Conducted an ML-driven data analysis to segment donors. Identified key factors to increase donations from newsletters.

OUR SERVICES

Our Services - Machine Learning & AI, Software Development, Data Visualization & Dashboards, Data Driven Business Strategy, Data Driven Marketing, Data Management & Strategy

TESTIMONIALS

Good360
“Each of the customer-facing consultants were professional and mature beyond their years. The team was adaptable to various challenges and scope adjustments necessitated by the project and ultimately delivered several PowerBI dashboards that will have ongoing value to Good360. I would definitely recommend the Berkeley Data Story team for supplemental BI and Data Science projects.”
- Kniffen Kelly, Sr. Director of Business Intelligence Center of Excellence at Good 360

ADDITIONAL PAST CLIENTS

Additional Past Clients - SimpleLab, IBM, GIG Car Share, Leaf, Plan International, LifeMoves, Fingenic