Jen Arriaza

Logo

Data Scientist
NY Metro

I develop analytical tools to solve industry challenges and create strategies based on quantitative insights.



Navigate to: Current Projects | Publications | Past Projects | About | Contact


Featured Projects

Predicting Failures in High-Risk Production: Aircraft Engines

Evaluating deep learning models to predict failures in high risk production environments.

Classification of Crash Severities & Pre/Post COVID Analytics

Random forest classifier model predicts crash severities in NYC and full report of insights from analytics deep-dive.

Data Science Internship at BMW’s Autonomous Driver Team

Large-scale data analysis and applied machine learning to improve testing and implementation of autonomous driving features.


Publications

Published: Investigating End-user Acceptance of Last-mile Delivery by Autonomous Vehicles in the United States

Co-author. Contributed as student data scientist in completion of academics at NYU. Accepted for publication in May 2022 to Human-Computer Interaction International 2022, and printed to Springer Digital Library.

View Publication

Published: Sulforaphane Effects on Cognition and Symptoms in Schizophrenia: A Randomized Double-Blind Trial

Co-author. Contributed statistical data analysis on published biomedical research study surrounding the effects of a novel low-toxicity drug. Accepted for publication March 2022 in Oxford Academic.

View Publication

Senior Research Project: A Study of Autonomous Vehicles: Background, Current Issues, & Outlook of Self-Driving Cars

In-depth research study examining AVs within the automotive/mobility industry.

View Paper


Back

Past Projects

Analytics Engineering

Trend Analysis in Python using Plotly visualizations. Analyzing historical waste/recycling trends.


Statistical Data Analysis

Linear Mixed Models in SAS Studio. Modeling outcomes of wide-format data and repeated measurements.


Academic Projects

Supervised machine learning in Python to find the cleanest eateries in NYC using health inspection data.


View Archive