Why New Horizon Multi-Echelon Inventory Optimization?

1. Reduce inventory position while improving customer service level through system optimized inventory policy (e.g. days of coverage, service level, hard number). The recommended policy has been verified using specified duration of historical time, so that you feel confident to switch it on

2. Dollarize the value add and project improvement of the service level and inventory position

3. Determine the minimum amount of inventory needed in order to keep the service level at a specified percentage

4. Generate a watch list so that users can focus on improving forecasting for specific items as needed.

Inventory Optimization: Challenges and Opportunities

While most companies can set up their safety stock using either desired customer service level or days of coverage approach, they experience these common and frustrating problems:

  • Difficult to Predict Service Level: It’s difficult to predict what service level one will get until a few months later. Why? Because inventory policy will not affect inventory until months later due to lead time.
  • Unforeseeable Inventory Problem: It’s hard to foresee how the demand and supply planning will fare until a few months after implementation. By that time, any damage due to over or under stock will have already been done. And users will need to re-adjust the inventory policy and then wait again to see the results. Basically, you’re constantly working from behind and trying to play catch up.
  • Hard to Suit Demand Planning System: Every single demand planning tool is different. How can the safety stock policy be adjusted so that it fits best for the demand planning tool in use?
  • Tough to Obtain Problematic and Opportunity Item List: It’s tough to go through hundreds of thousands of products to find the problematic few, as well as the opportunity items, based on old and outdated inventory policies and procedures.

The New Horizon Solution

New Horizon Multi-Echelon Inventory Optimizer (MEIO) was designed and developed using unique machine learning technology. The tool utilizes historical service level and inventory to optimize the safety stock settings.

  1. Conducts machine learning using historical performance. This is no assumption of normal distributed noise, as is used by competitors
  2. Optimization of the safety stock setup is tailored to demand algorithms used
  3. Simulate what will happen using the current safety stock policy, identify issues and problems before they can happen
  4. Identify problematic items and opportunity items so that we can focus on them during demand forecasting and supply planning

Results

Below listing a three typical customers achievement. After using the tool:

  • Customer one achieved a 33% inventory reduction, all while still meeting the current customer service level.
  • Customer two achieved a 16% inventory reduction, all while meeting a high customer service level. Demand forecasting on the top 10% problematic items was the key focus for this customer.
  • Customer three achieved a 21% inventory reduction, while still meeting the high customer service level they had planned to meet.