Altria's challenge
Unplanned employee absences at Altria's Philip Morris USA manufacturing plant were threatening to increase labor costs and reduce overall production if not properly forecasted.
The assignment
A team of MBA students from NC State were tasked with creating an automated, data-driven model that Altria could use to more accurately forecast unplanned absences at their manufacturing plant.
The students' approach
The students started by obtaining key data from Altria, including historical staffing information. They organized it by department, shift, job title and date to create a database of historical unplanned employee absences.
The team used four data sources provided by the company to create the database:
- Production calendar
- Headcount
- Cost center
- Employee absentee data
The team then used business analytics software to create a predictive model that could forecast unplanned absences by day of the week, shift and job title.
The forecasting model included three data exploration factors:
- Absentee rate by job class, shift, day of week and month
- Absenteeism by hire date
- Standard deviation in absentee count by month, year, and job class
Outcomes
Altria managers can now use the model to forecast otherwise unpredictable human behavior, i.e. unplanned employee absences.
By incorporating trends such as seasonality, the model can produce more confident, accurate results.
Additionally, the accuracy of the model should improve over time as more historical data is added.
When supplemented with the existing knowledge of Altria’s production management teams and staffing supervisors, the tool should allow the company to implement strategies that will reduce labor costs while keeping production on schedule.
“Because of this project, our organization better understands previous employee behavior. We utilize the project output to review historical trends prior to calendar holidays or production calendar changes. The students were professional, organized, and thoughtful in their approach. They communicated appropriately and actively participated in our team calls. They also took feedback and adjusted their work to improve the project deliverables. Overall, it was a great experience and I enjoyed working with the NC State students.” — Ryan McGowan, Sr. Manager, Production Support, Altria
“After the time it took to understand Altria’s complex staffing structure, it was challenging to create a more-than-satisfactory deliverable, and it required best efforts from everyone involved. Altria and our team advisor were very supportive throughout the project. The opportunity to work with the company on a weekly basis and to gain experience solving a real-world problem was invaluable. Overall, the opportunity to work with Altria and our advisor to solve a complex problem was a great experience. I learned a lot and definitely made progress in building both soft and hard skills!” — Pranay Shah, Jenkins MBA alumnus
“I think the team gained valuable experience in working in a complex manufacturing environment with lots of moving parts. They were frequently provided new or revised data which then had to be incorporated into the model and/or the model modified. In addition to gaining experience in modeling, the team exceled in managing the project and client expectations, as well as communicating with multiple stakeholders.” — Tracy Freeman, NC State faculty advisor
_______________________
_______________________
The NC State team
Michael (Lloyd) Jones
Robert (Bobby) Williams
Pranay Shah
Tracy Freeman (faculty advisor)
The Altria team
Ryan McGowan - Sr. Manager, Production Support
Paul Kwolek - Assoc. Manager, Manufacturing