Goodpack Transforms S&OP Process with Artificial Intelligence and Advanced Analytics



Goodpack is a world leader in steel Intermediate bulk containers (IBCs), a multi-modal, reusable metal box system that provides packaging, transportation, and storage for global industries.  Goodpack owns and operates more than 4 million IBCs across 78 countries at 442 depots, 352 ports, and 8,031 customer locations.

An IBC is a large vessel that stores or transports fluid and bulk materials. Goodpack rents IBCs to customers. Customers rent IBCs, with Goodpack delivering the IBC to the customer's specified location and retrieving it on rental expiration.

Identifying customer demand, locating inventory in the right location, delivering the IBC and retrieving IBCs involves a complex series of decisions. Goodpack’s primary challenges were to improve asset utilization, reduce unproductive transport costs and decrease delayed or lost revenue.

"We were impressed by Antuit’s domain expertise and ability to demonstrate the positive impact of advanced analytics on our business. I’m confident that Antuit’s platform will transform our supply chain planning into a data-driven, customer-centric strategic business enabler."

Kenneth Hee

CIO, Goodpack


To address these challenges, Goodpack retained Antuit to transform their global S&OP process. The existing planning team lacked an analytical decision support engine that could enable optimal business decisions and as a result, drive effective sales and operations planning/ S&OP cycle. 

Antuit deployed its planning and analytics platform, OPTIMUM, to address these challenges.

Antuit assembled a team of business consultants, statisticians, operation research scientists, and technologists to build the solution. The team combined technology, science and domain expertise to transform the client’s S&OP process radically and unlock value.

Solution specifics:

  • Forecasted supply and demand using proprietary machine learning techniques. Built an ensemble of 20 advanced statistical models, plus a custom statistical model to consider specific business complexities
  • Created an optimization mechanism to globally assign inventory to the right location, to meet the demand at the lowest cost without compromising service levels
  • At an operational level, designed an order allocation algorithm to allocate inventory to the sales orders based on the business rules and to build efficient truckloads
  • Implemented an easy-to-use scenario workbench capable of running multiple scenarios in parallel
  • Configured an Inbuilt visualization platform to deliver various reports, KPIs, and insights
  • Re-designed S&OP process aligned with industry best practices
  • Provided comprehensive training program to central planning team and key stakeholders that covered the new S&OP process, statistical techniques deployed, and optimization concepts used. Also established a refresher training program to drive higher adoption of the solution.


Goodpack received sustainable and significant value through Antuit’s unique ability increase revenues and margins that yielded these results:

  • Established data-driven monthly S&OP process
  • Improved forecast accuracy for key business verticals in the range of 5-12%
  • Data science team continues to refine the statistical models by incorporating business nuances, outlier treatment, and other advanced techniques. It helps to continually improve the forecast accuracy
  • Estimated transportation cost reduction by 14-17%



OPTIMUM is Antuit’s cloud-based planning and analytics platform built for modern data-driven digital supply chains. Some salient features include:

  • Powered by artificial intelligence with industry-specific algorithms, plug-and-play integration, and an intuitive configurable user-interface
  • Custom machine learning algorithms can be built specific to a business / industry construct
  • Scenario development and analysis capability is available to support S&OP process
  • Support for ongoing analytics-as-a-service to ensure superior adoption and focus on driving value
  • Speed to value / implementation time frame is less than 6 months



Download the case study

Download now