Josh Scherer

Data Scientist

About

Hey! I'm Josh.

I'm a current senior at Vanderbilt University studying Computer Science and Applied Math with a minor in Data Science. Over the last few years, I've had the opportunity to study and use Machine Learning concepts in the real world. With projects ranging from optimizing traffic flow on major US interstates to predicting customer reliability, I have a broad range of experiences under my belt that I'm excited to utilize in future opportunities.

Data Scientist

I am originally from Birmingham, AL and currently studying in Nashville, TN. However, I am open to relocating to another area of the country to explore new opportunities.

  • Email: joshua.r.scherer@vanderbilt.edu
  • Phone: (205) 757-3235
  • City: Birmingham, AL
  • Resume: Click Here to View

I am looking to join a team as a Junior Data Scientist (Data Scientist I) or as a Data Analyst as I step into full-time employment. I am also open to using my versatility to embrace a more development-focused role as a Software Engineer should the right opportunity present itself.

Skills

Click on any of the categories below to view my specific skills.

Python 90%
C++ 80%
C 75%
Java 75%
R 70%
Rust 55%

SQL 90%
MongoDB 80%
Spark 75%
Hadoop 75%
Pandas 70%

Matplotlib90%
Seaborn85%
Plotly70%
ggplot260%
PowerBI75%
Kibana60%

Scikit Learn80%
PyTorch75%
AWS SageMaker70%
Tensorflow70%
Keras70%

Regression (Linear, Polynomial, etc.) 90%
Classification (Logistic, SVM, etc.)90%
Neural Networks70%
Clustering (KMeans, DBSCAN, etc.)90%
Ensemble Techniques (Random Forest, XGBoost, etc,)75%
Regularization Techniques80%

Professional Experience

I've been fortunate to engage in a variety of professional experiences across an array of industries, each offering unique challenges and opportunities for growth. These roles have not only honed my technical abilities but have also allowed me to develop an understanding in how to make meaningful contributions in a professional setting.

Professional Experience

Approck Cloud

Machine Learning Engineer

Birmingham, AL

Sept 2023 - Present
  • Streamline data modeling process via cloud computing services including Amazon Web Services' SageMaker
  • Forecast order cancellations, supporting operations for the largest heavy construction software company in the world
  • Establish a credibility metric across customers to save concrete suppliers hundreds of annual driving hours

AvidXchange Inc.

Data Scientist Intern

Charlotte, NC

June 2023 - Aug 2023
  • Leveraged survival curves to formulate a comprehensive risk index for 500,000+ users, informing strategic decisions
  • Investigated and refined various regression modeling techniques, leading to more precise data-driven predictions
  • Delivered crucial findings to company executives, playing a critical role in the model adoption process

Institute for Software Integrated Systems

Research Assistant

Nashville, TN

May 2022 - Present
  • Architected an AI decision support system used to optimize traffic flow along a 28 mile stretch of I-24
  • Constructed an interactive graphical representation of a 200+ device network using GIS data queries
  • Deployed an automated solution for seamless, real-time analysis of extensive weekly traffic data streams

Vanderbilt University

Teaching Assistant: Digital Systems

Nashville, TN

Aug 2022 - May 2023
  • Offered timely feedback through graded homework and clarified students' questions to enhance comprehension
  • Identified, articulated, and addressed student concerns, ensuring a conducive learning environment

Portfolio

Click on any of the images below to check out my projects.


Charlotte Geolocation Exploration

Before I moved to Charlotte for the summer, I decided to try to gain a better understanding of my new city. To do so, I used a combination of tools including AWS EC2, AWS S3, Spark, Python, and SQL to translate numerical traffic and crime statistics into a visual representation of aggregate trends. Additionally, I implemented an address-lookup system using Levenshtein distance to allow for imperfect user inputs.


Rubik's Cube Project

In order to display my understanding of object oriented programming and key concepts in linear algebra, I implemented a Rubik's cube in Python that allows for rotations and tracks states. This representation serves as the basis for a larger project where I am creating murals out of a collection of cubes. Currently, I am finalizing visually representing the cube using JavaScript's THREE module and implementing a reverse solving algorithm.


Alzheimer's Classification

As a part of my final project for my Machine Learning class, my group and I explored tactics used in image processing and mitigating underlying biases in datasets. We found a dataset of MRI scans of Alzheimer's patients at various stages of the disease. We applied ML concepts including PCA, KNN, K Means Clustering, Logistic Regression, Support Vector Machines, and Convolutional Neural Networks.

Awards

Below, you will find a few of my proudest academic achievements.

Vanderbilt School of Engineering Dean's List (All Semesters)

Maintained a semester GPA above 3.5 for each semester, demonstrating sustained academic excellence throughout the program's duration.

National Merit Commended Scholar (Finalist)

Scored in the top 0.5% of all students across the state of Alabama in the PSAT and performed well in academically rigorous coursework.

National AP Scholar (2020)

Achieved an average score of 4.3 out of 5 across 10 Advanced Placement exams, showcasing a breadth of understanding across an array of subjects.

Pi Mu Epsilon Honor Society (2023)

Recognized for outstanding achievement in mathematics through demonstrating a consistent commitment to the advancement of mathematical sciences.

Publications

Cooperative Multi-Agent Reinforcement Learning for Large Scale Variable Speed Limit Control

2023 IEEE International Conference on Smart Computing (SMARTCOMP)

View Publication