Penn State University Industrial Engineering Ph.D. student
Utilizing Machine Learning to improve design processes in the Smart Design and Manufacturing Systems Lab.
A website for univeristies to help students find jobs.
Iowa State University: Master's Degree
I worked with Janis Terpennny on developing product obsolescence forecasting frameworks.
NewLink Genetics: Financial Analyst Intern
Constructing financial models and deconstructing investment bank evaulations.
Iowa State University: Bachelor's Degree
Double major in Industrial and Manufacturing System Engineering and Economics.
National Science Foundation: Center for eDesign
Hired to conduct research in engineering design.
Bio. I am currently a PhD student in industrial engineering at Pennsylvania State University, working with Janis Terpenny. My work centers around machine learning and data visualization and its applications in design and manufacturing. For example, I developed a machine learning based product obsolescence forecasting framework (ORML & LCML). I am currently working on building applications around the highly accurate product obsolescence forecasting framework, including more effective life time buy management and feature requirement gathering tools.

In my free time, I enjoy working on data visualization projects, hackathons and studying economics. A product of all three of these loves is PlacementGlobe.com. Placement Globe was developed over a weekend at HackISU and is a data visualization tool for colleges to map student placement history. The goal is to help students find employment in different regions of the country and to help better understand expected salaries.

Projects and Publications

Obsolescence Risk Forecasting and Life Cycle Forecasting using Machine Learning
The ORML and LCML methodologies were developed out of a research project through The Center for eDesign. Obsolescence Risk Forecasting using Machine Learning (ORML) uses the specifications from current and past products or components in a market place to predict the likelihood a product is discontinued or actively in production. Life Cycle Forecasting using Machine Learning uses the same product specifications to predict the date a product will most likely become obsolete. This research is being continued at the Smart Design and Manufacturing Systems Lab at Penn State. If you are interested in collaborating on this research, feel free to contact us.
Connor Jennings, Dazhong Wu, Janis Terpenny
IEEE Transactions on Components, Packaging, and Manufacturing Technology
Placement Globe
Placement Globe allow universities to plot on a map where past students work. The map can be moved and zoomed and then returns a list of companies and job titles in the area that have hired students from the university. Jobs can be filtered by college, degree, degree level, internship or full time, and searched. A histogram displays salaries from the filtered jobs in the region.
Connor Jennings
Taxonomy of Factors for Lifetime Buy
This paper takes on optimizing lifetime buy decisions by investigating the myriad of factors impacting total costs. A taxonomy is put forward that provides the basis for a comprehensive decision support tool, capable of assisting lifetime buy quantity decisions over the product lifecycle.
Connor Jennings, Janis Terpenny
ISERC 2015
Life-Time Buy Confidence Simulation
The Life-Time Buy Quantity Calculator is a Microsoft Excel extension that uses a Monte Carlo simulation technique that pulls from many probability distributions and creates numerous scenarios. These scenarios are then analyzed to predict the optimal order quantity when placing a life-time buy order.
Connor Jennings
NSF: Center for eDesign

Talks and Other Links

Life Cycle Cost Trade-off Model: Comparison of Life Expectancy and Quality on Overall Cost
Connor Jennings and Janis Terpenny
Obsolescence Risk Forecasting using Machine Learning
Connor Jennings, Dazhong Wu, and Janis Terpenny
MSEC 2016
Product Life Cycle Forecasting using Machine Learning
Connor Jennings, Dazhong Wu, and Janis Terpenny
ISERC 2016