A few potential opportunities that vary in technical and political complexity. I need to line up support internally before being able to commit to any of the following:
A) Predicting work content
We operate a number of heavy repair facilities for performing maintenance and upgrades on our railcar fleet. When a car is scheduled for maintenance and arrives at a shop, the extent of labor required is not known until the car is thoroughly inspected and an estimate is written. Miles traveled, # loads/unloads, commodity properties, customer handling, etc. all can influence the amount of repair work required. Being able to better predict maintenance would improve scheduling of rail cars and allocation at different shops.
We have a rudimentary system in place based on random forests built in Python (pandas, scikit-learn, Orange) / Excel, but it needs refinement.
Blue sky objective would be to build this insight into a tool that helps direct shop loading decisions (e.g., can we justify sending this car 500 miles further away to a shop with more available capacity?).
B) Predictive Maintenance
Our engineering group is dipping their toes in this space. They recently completed a project to predict the need to replace worn wheels in advance of exceeding a threshold which allows the railroad to perform the replacement at a high cost to us. Not sure what else our engineers might be pondering, but I’ll look into it.
C) Inventory Optimization
We are in very high-mix / low-volume space with many of our externally sourced components and also experience variable demand and lead times. There is an opportunity for analysis of current material management costs (carrying costs, stockout cost, inventory space) and optimum management strategy.
Course Info & Engagement Details
|School||Masters in Business Analytics (MSBA)|
|Course||MSBA Capstone (SPRING 2020)|
|Students Enrolled||5 Students per Group (61 Enrolled in Program)|
|Meeting Day & Time||Monday OR Wednesday (3:00 - 4:50 PM ET)|
|Student Time Commitment||8-15 Hours Per Week|
|Company Time Commitment||2 Hours|
There are currently no supervisors assigned.
There are currently no students assigned.
|Touchpoints & Assignments||Due Date||Submission|
Key Milestones & Project Process
February 7, 2020 - Define
Introduction to GATX’s business with a focus on rail car repair operations. The current process and preliminary data will be shared with students for initial exploration.
The goal of the project is to predict expected labor hours required in several categories of repair (cleaning/commodity flare, mechanical, interior blast, interior lining, exterior paint) using known characteristics of the car. Accurate labor predictions will inform future loads on labor and can predict expected cycle times of repair events.
- Define data scope (time period, data items)
- Finalize milestones and project charter
February 28, 2020 - Measure/Analyze
The data provided will be from production databases and will be shared in its raw, unclean state. It will need to be cleaned/wrangled into something that is suitable for input into a machine learning algorithm.
Once in a manageable state, the team will need to decide which data is relevant to the problem at hand. Feature selection can be justified with statistics or by knowing the relationship between the feature and the target.
- Feature selection
- Regression model selection
March 27, 2020 - Improve
The team will develop a method for applying predictive analytics and evaluate the effectiveness of their method.
This method will be used by the business user(s) on an on-going basis to evaluate current loads and inform daily operational loading decisions. As such, the method must be well-defined and programmatic. Required inputs and generated outputs must be documented for repeatability.
- Specification of the training input file (time scope, file format, column names, data types, etc.)
- Specification of the prediction input file
- Specification of the output file
- Training program/script
- Final prediction program / script
- Evaluation of model (cross-validation scores [R², RMSE, MAE, etc.] and known issues)
April 17, 2020 - Control
Define how the technical output can be utilized by the business for sustained effectiveness.
Identify any known gaps in the final model and suggest solutions for these gaps.
- Mockups/suggestions for the front-end user interface for use by the operations scheduler and shop management
- The final report out (slide deck, white paper, or similar) targeted toward management
–Audience for the report should be assumed to be technical (familiar with stats) but not experts in ML or predictive analytics
–Target ~15-minute presentation or ~5-minute read
There are no resources currently available