Assigns demand nodes to supply points so that the resulting network has least possible network load.
SB SND Modules
Values Delivered
Geo Spatial Optimiser
Efficient Assignment of stores to branches
Cost optimisation
Improved service aspiration
Minimised salesman travel distance
Minimal last mile costs
Multi modal transport optimisation
Vehicle Route Planning Optimiser
Assigns the right vehicle for each supply x demand x product lane

Assigns the right vehicle to the right source x destination x product mix
Maximises VFR while minimising total Transport Distance & Network Load
Cost optimal milk run route
Respects Capacity, vehicle availability and expected service frequency constraints
Inventory Optimiser
Recommends the right inventory based on lead time, cycle time and service level

Recommend inventory norms based on the expected SLA and resilience/responsiveness needed
Evaluate the responsiveness of an existing inventory norm
Exploit demand aggregation benefits
Reduce Under Performing Inventory
Leverage existing supply network to recommend zero inventory branches
Business Capabilities

2M+
Retailer’s assignment handling capability

10000+
SKUs handling capability

200+
Production facilities

2000+
Inventory & warehousing facilities

20+
Times Period

500,000+
Lanes
Technical Capabilities
Polaris uses a Mixed Integer Linear Programming model (MILP) for solving its supply network design problems

20M
Continuous variables

25M
Constraints

4M
Integer variables

0.1% in 1HR
Optimality Gap of running
Benefits

$14.7M PA
Cost Saving per annum up-to

$15M
Inventory reduction per annum

1.1 Day
Last leg Lead time improvement

1.6MT
CO2 emissions reduced per annum

100000 sqft
Warehouse size reduction

15%
Reduction of effective Network length

10%
10% increase in Vehicle utilization

12%
Direct to customer shipment improvement