Active users
Employees
At a glance
Challenge
Atlas Van Lines needed to find a way to adjust their capacity and price based on future market demands.
Result
Pariveda assisted Atlas in building a machine learning model. This model reliably predicts the demand by region, every day, for up to six weeks.
Impact
Atlas’s operations team can now quickly see which days need extra attention. This results in significant cost savings due to decreased shipment delays.
Atlas Van Lines, Inc., is comprised of more than 430 companies in the U.S. and Canada, plus 1,500 global partners in 17 countries. The company is based in Evansville, Indiana, and offers local, long-distance, and international moves.
The Challenge
Atlas needed to predict demand for long-haul moving in order to price dynamically.
During peak moving seasons, the Atlas agent network of Atlas Van Lines works together across markets to meet customer demand. However, their ability to forecast capacity had been completely manual, and labor intensive, relying on the wisdom of people with many years of experience and, admittedly, their gut instincts. Atlas possessed the historical data from 2011 forward and desired to find a way to dynamically adjust capacity and price based on future market demands.
The Result
How Pariveda helped Altas predict demand:
- Using Agile Machine Learning (AgileML) methodology, Pariveda went through an identify- and-assess phase to ensure that the problem statement was clearly identified.
- We then assisted Atlas in building a Machine Learning model by implementing sophisticated feature engineering and training 252 individual models, which predict the demand (in lbs.) by region, every day, up to six weeks into the future.
- Each day, the results of the predictions are displayed in a heatmap that enables quick line-of-sight into days with excess demand and days with excess capacity.
The Impact
The new model allows Atlas’s operations team to quickly and reliably see which days will require extra attention. This results in significant cost savings due to diminished shipment delays. Additionally, the marketing team can now see which days may require additional effort to secure enough orders to fill capacity.
Pariveda developed a Machine Learning approach to logistics-demand forecasting that enabled new operational efficiency.
Related specialties
SERVICE
Artificial Intelligence
SERVICE
Technology & Digital
Learn how we deliver on the essential, strategic needs that enable companies to sustain a resilient and impactful business.
Case Studies
Explore more success stories
INSIGHTS
Article
Article
Perspective
Article
Perspective
Article
Perspective
