Joshua Roberge
Londonderry,NH
Summary
Detail-oriented Data Scientist with 4 years of experience in Machine Learning and data analytics, currently excelling in a role at Westinghouse Electric. Proven track record of delivering actionable insights and data-driven solutions that improve business operations and drive growth. Skilled in a variety of statistical analysis tools, programming languages, and data visualization software. Committed to maintaining the highest standards of accuracy, integrity, and professional ethics. Known for clear communication and ability to explain complex data concepts to stakeholders at all levels. Seeking to leverage my expertise to help organizations make data-driven decisions and achieve their objectives.
Overview
15
15
years of professional experience
Work History
Data Scientist
Westinghouse
Cranberry, PA
10.2020 - Current
- Using a Siamese network, built a search algorithm for nuclear parts product matching
- Developed a hierarchal, multi-class and multi-label text classifier that predicted UNSPSC product codes for the nuclear industry
- Served as lead mentor for Westinghouse's 'Data Citizen' program
- Built a time to event model for the department of energy
- Served as a data scientist for the DOE 'The Light Water Reactor Sustainability Program' contract
- Created a UNSPSC Power Bi dashboard which increased the accuracy and efficiency of the annotation process
- Established benchmarks for the effectiveness of a labeling schema
- Designed a targeting annotation algorithm which increased the efficiency of the annotation process by over 1,800%
- Using topic modeling, cleaned and normalized data for the DOE
- Regularly presented progress to non-technical stakeholders.
- Enhanced data-driven decision making by implementing machine learning models and algorithms.
- Optimized business processes for increased efficiency through detailed data analysis and visualization tools.
- Collaborated cross-functionally with stakeholders, ensuring alignment on key initiatives and project goals.
Data Analyst
Southern New Hampshire University
06.2020 - 10.2020
- Using Power Bi designed dashboards for reporting progress on the genesis project
- Created automated data lineage visuals that allowed the business to understand how and where their data was being used
- Crafted an app that brought together multiple tools and reports
- Constructed crosswalks that allowed data to flow from one system to another
- Acted as a liaison between the business community and the DBA team.
Data Science Consultant/Intern
Fresh Air
Lebanon, NH
01.2019 - 05.2020
- Using an FCN-LSTM neural network, developed an algorithm that recommends which sensor alerts were important and needed to be reviewed by an analyst
- With times series data, feature engineered over 150 features
- Using XgBoost, Random Forest, Neural Networks, and SVM's built an ensemble model that used a voting system
- Communicated with clients and guided expectations towards practical solutions
- Delivered a product that would save 70,000 labor hours.
Data Science Consultant/Intern
RiverStone
01.2019 - 05.2020
- Using Python and Power Bi, created an information security dashboard that brought together multiple systems into one cohesive environment
- Using an autoencoder, designed a latent variable model that described IT risk across Riverstone.
Squad Leader
United States Marine Corps
01.2009 - 01.2015
- Deployed as a military lead instructor for an Afghan National Army training post
- Tasked to lead, train and mentor 12 Marines in a kinetic environment
- Assisted with the logistical management of 30 Marines while in Afghanistan
- Served as a liaison between local leaders and private contractors to help run a boot camp for local soldiers
- Recommend leadership positions based on performance reviews.
- Enhanced team cohesion with regular debriefings, feedback sessions, and team-building exercises.
- Improved squad communication by implementing new strategies and protocols in daily operations.
Education
Master of Science in Analytics -
University of New Hampshire
01.2020
Bachelor of Science in Economics -
University of New Hampshire
01.2019
Associate of Arts -
Great Bay Community College
01.2016
Skills
- Intelligence Gathering
- Business Forecasting
- Statistical Analysis
- Data Mining
- Machine Learning
- Python Programming
- Data Visualization
- NoSQL Databases
- Data Visualization
- Big Data Analytics
- Natural Language Processing
- Anomaly Detection
- Neural Networks
- Scikit-Learn
- Deep Learning
- Databricks
- Generative AI / Transformers
- Docker/Kubernetes
- Azure
- Power BI
- Spark
- Analytical Thinking
- Business Requirements Gathering
- Feature Engineering
Areas Of Knowledge
- Machine Learning/Statistics: CART (Random Forest, XgBoost), feature selection, anomaly detection, class imbalance techniques, clustering, dimension reduction, hyperparameter tuning (Bayesian optimization), text embedding techniques (Bert, Doc2Vec, Word2Vec), topic modeling, Artificial Neural Networks, Natural Language Processing (NLP).
- Programming/Coding: Python, SQL, PySpark, R, Keras, TensorFlow, Pytorch, Scikit-Learn, NumPy, SpaCy, Gensim, NLTK, Pandas, SciPy.
- Visualization/Dashboarding: Matplotlib, Seaborn, Plotly, GGplot, Graphviz, Tableau, Power Bi, Dash
- Software/Big Data: Spark, Databricks, Azure, MlFlow, Git
- Business/Soft Skills: Agile, leadership, organization, critical thinking, communication, business intelligence
Timeline
Data Scientist
Westinghouse
10.2020 - Current
Data Analyst
Southern New Hampshire University
06.2020 - 10.2020
Data Science Consultant/Intern
Fresh Air
01.2019 - 05.2020
Data Science Consultant/Intern
RiverStone
01.2019 - 05.2020
Squad Leader
United States Marine Corps
01.2009 - 01.2015
Master of Science in Analytics -
University of New Hampshire
Bachelor of Science in Economics -
University of New Hampshire
Associate of Arts -
Great Bay Community College