Machine Learning and Inventory Optimization Accelerate Success for Uni-Select
Uni-Select is a leader in the distribution of automotive refinish and industrial paint and related products in North America, as well as a leader in the automotive aftermarket parts business in Canada and in the United Kingdom.
Demand fluctuation, particularly around seasonality, is a major challenge. Despite its efforts to improve processes, inventory management performance did not reach target levels.
In a calendar year since implementing Automatic Policy Tuning (APT), a capability within Manhattan Demand Forecasting and Replenishment, Uni-Select has achieved striking results, including:
- Reduced inventory
- Better fill rates
- Significantly fewer demand for exceptions
- Reduced manual changes
- Increased planner productivity
- Improved receiving dock performance
The challenges of seasonality on demand in one of Uni-Select’s distribution centers resulted in excess inventory and a higher level of exceptions.
Leveraging Manhattan Demand Forecasting and Replenishment with Automatic Policy Tuning capabilities.
The inventory carried in the distribution center was reduced, resulting in significant savings.