Darren Fishell

Business Intelligence Leader & Data Scientist

Los Angeles, California, 90025

Email • LinkedIn • Github • Tableau Public

SUMMARY

Data scientist and business intelligence leader with 7+ years experience designing metrics, building data pipelines, and delivering actionable insights that drive business decisions. Data visualization expert with 10+ years experience with Tableau and 5 years experience in Power BI. Combines technical expertise in SQL, Python, and machine learning with proven ability to collaborate across departments. Experience built leading small, agile teams through greenfield development, navigating ambiguity guided by a fundamental understanding of the toolkit and best practices.

EDUCATION

M.S., Data Science
Northeastern University • Portland, Maine
Jan 2020 — Jan 2024
GPA: 3.77 • Studied a range of techniques in supervised and unsupervised learning, data cleaning and management, predictive modeling, model analysis, avoiding false discoveries and large language models.

B.A., English, Minor Italian
Bowdoin College • Brunswick, Maine
Jan 2005 — Jan 2009
GPA: 3.55; English GPA: 3.91

WORK EXPERIENCE

Business Intelligence Manager

Baker Newman Noyes • Portland, Maine, United States
Jul 2022 — Present

Defined enterprise BI strategy including architecture for self-service semantic models enabling role-based metrics access in Excel and Power BI
Established data governance reports for Finance teams, identifying inconsistencies across disparate systems
Developed client rating scorecard and profitability metrics with executive leadership, reducing time-to-bill through custom alerts and unified semantic models
Integrated additional sources into Power BI environment, using a variety of ETL techniques, including direct PowerQuery access to REST APIs. Data integrated included Paylocity, JIRA, Business Central, Microsoft Teams, Varonis, Active Directory and ManageEngine
Presented to BNN clients on evaluating AI tools and large language models for business applications during the company’s annual client update

Business Intelligence Analyst

Baker Newman Noyes • Portland, Maine, United States
Jun 2021 — Jul 2022

Engineered unified snowflake schema that transformed 20+ fragmented reports into a cohesive data architecture with real-time analytics, developing a new data reporting model for the IRIS STAR Practice Management system, which required intensive investigations and requirement gathering as the database vendor does not provide an ERD or data dictionaries for its database
Created the company’s Power BI tenant architecture and app-based distribution model, supporting 350+ users across tax, audit and advisory practices and all staff levels
Implemented novel report-level security in Power BI allowing report preview as any user, reducing development cycles and bug resolution times
Supported ad-hoc business requests for data access and data updates

Senior Consultant, Business Intelligence

Arkatechture • Portland, Maine
Nov 2018 — Jun 2021

Built and maintained reports in Tableau, Power BI and upstream database views in Snowflake for major retailers, including Cole Haan and SONY
Originated work and built the Maine CDC’s first public COVID-19 dashboards, which was the primary source of statewide information on daily case trends. The state’s pandemic response was rated #1 in the contiguous U.S. by the Commonwealth Fund
Built and maintained serverless data pipelines in AWS Lambda and Snowflake warehousing solutions for major digital gift card company
Conducted advanced market basket analysis for regional coffee chain and delivered Tableau training for multiple client organizations, including for Arkatecture’s credit union reporting product

Data Journalist and Investigative Reporter

The Bangor Daily News • Portland, Maine Area
Apr 2014 — Oct 2018

Conducted analysis of retail electricity pricing that led to a $14 million class-action settlement and established methodology adopted by state regulators
Built interactive data visualizations to communicate complex economic trends and enhance investigations of property records and court filings
Developed automated pipelines to track campaign finance data, creating transparency around political influence in state politics
Keynote speaker at the inaugural conference of the University of Southern Maine’s Data Innovation Project

SKILLS

Python
ANSI SQL
scikit-learn
pandas
Git
Data visualization: PowerBI, Tableau, Observable
Semantic modeling
Natural language processing
DuckDB
Writing
Research
Public speaking & presenting

PROJECTS

Cost analysis for Maine’s residential retail electricity suppliers

Portland, Maine • Jan 2015 — Present

Developed a data pipeline and framework for comparing cost of Maine’s retail electricity supplier prices to the state’s standard offer. This framework was validated and adopted by the Maine Public Utilities Commission in their own study. The analysis revealed Maine customers could have saved $180.5 million from 2012-2024. Initial analysis at the Bangor Daily News was done manually and visualized in Tableau. The updated project uses dlt for data ingestion, dbt for transformations and the Observable Framework to display interactive visualizations.

Semantic similarity analysis in Maine legislative testimony

Portland, Maine • Sep 2024 — Present

Built end-to-end pipeline for 20,000+ bills with semantic clustering (0.535 silhouette score) and vector embedding system for 3.6M sentences using HuggingFace transformers. Created vector search in DuckDB for real-time similarity queries, enabling analysis of testimony influence patterns for Sierra Club advocacy.

Portland, Maine • Jan 2024 — Dec 2025

Refactored brittle Perl/VBA pipeline with Python ETL for Medicare EDI 835 files and PDF remittance advice, implementing pattern-based extraction, DuckDB storage, and SQL view transformations. Cut annual development costs by 90% while improving modularity, speed and data quality.

Bias detection in Paycheck Protection Program funding

Portland, Maine • Jan 2022 — Jun 2022

Identified statistically significant biases in PPP loan distribution during COVID-19 by integrating multiple data sources and applying regression modeling that controlled for confounding variables including rural-urban differences and industry concentration.