PECO Pallet Improves Forecast Accuracy and SI&OP with Demand Analysis Tool

Coupa
Read time: 4 mins
PECO Pallet Improves Forecast Accuracy and SI&OP with Demand Analysis Tool

With the continued rise in supply chain complexities and market disruptions, formulating accurate demand predictions becomes a key element in supporting data-driven decisions across the enterprise. Traditional forecasting tools can be influenced by bias, fail to identify complex trends, and lack the ability to incorporate external factors such as GDP or CPI. 

The emergence of Artificial Intelligence (AI)-powered demand analysis tools is enabling businesses to develop more accurate forecasts to support their decision-making and planning processes.

Benefits of Demand Forecasting using Coupa Demand Modeling

Coupa’s demand modeling capabilities help companies fortify their supply chains for resiliency in the face of disruption — optimizing supply chain and marketing operations, increasing sales, and better managing inventory to lower operating costs.

Customers that use Coupa have seen the following improvements:

  • Demand Forecast Accuracy: Coupa employs effective machine learning algorithms that use existing internal data and external sources to make more accurate predictions. 
  • Supply and Demand Planning: With reliable demand forecast results, businesses can direct their attention to other important supply chain issues rather than focusing on demand fluctuations.
  • Customer Satisfaction: Efficient inventory planning using demand forecast data reduces stock-outs, thus increasing customer satisfaction. 

The Case of PECO Pallet

PECO Pallet is committed to delivering quality wood block pallets and excellent service to their customer base of leading manufacturers of grocery products and consumer goods. Their extensive North American service network provides complete transportation coverage within the U.S., Canada and Mexico. PECO Pallet is headquartered in Irvington, New York, with over 1,600 pallet manufacturing, recovery, sort and full-service depot locations across North America.

PECO Pallet Supply Chain Cycle Graphic

The Challenge

PECO Pallet was challenged to generate an accurate network-level forecast. Experiencing 300% explosive growth over the last 10 years resulted in a dramatic change in their mix of renters, some with high-volume demand and contending with intermittent pallet returns from retail locations.

Their primary business objective was to generate a repeatable, trusted process for month-over-month top-down forecast for the upcoming 15 months to support sales, inventory and operations planning. They needed to improve their ability to predict and improve dwell time between pallet issue and return.

Each day the dwell time increased, there was significant capital investment required to maintain the needed pallet pool and honor committed service levels. Adding to this challenge, demand for each renter is impacted by different macroeconomic or external drivers. It was almost impossible to systematically quantify and generate a reliable forecast.

The Solution

PECO Pallet adopted Coupa’s demand modeling solution, utilizing clustering functionality, machine learning algorithms, and external causal data to perform customer demand analysis and generate a network level forecast.

PECO Pallet Supply Chain Solutions Graphic

Because the vast majority of PECO Pallet’s supply and demand is driven by a selection of top customers, they chose to predict pallet returns by doing a detailed analysis of a few key customers. They did this using Coupa’s clustering capability for the remainder of customer volume. In addition to the resulting overall forecast, they separated the large customers for individual forecasts.

They ran multiple models for each large customer and cluster group to determine what would drive future demand, applying different machine learning algorithms to hone the best result. Each group benefited from a unique set of techniques and external causals. For example, previous demand values, days in month, seasonal index, U.S. consumer price, and GDP were key causal drivers for one large customer.

Demand Forecast Results

“Within two months, we had a model in place that incorporated key external causals for 15+% improved forecast accuracy. This allowed us to generate better cross-functional monthly planning and focus our energy on more detailed analysis.” —John Solomon, Director, Transformation and Data Analytics, PECO Pallet

The customer has now made their new forecasting process repeatable by connecting with their live data warehouse. They use Coupa’s model output as part of their SOIP process and it is a key data point to set their supply/return for the coming months.

Take a Science-Backed, Outside-In Approach to Demand Predictions

Coupa's Demand Modeler can help your organization make better predictions and supply chain decisions. No matter your industry, you can empower your team by providing them with this effective tool to improve forecast accuracy and intelligently balance supply and demand. 

  • Apply a deep library of machine-learning algorithms to your historical demand models to understand signals in an unbiased way. Self-learn from complex demand patterns (e.g. seasonality) and find common segmentation groups to prescribe the best model for data-driven insights.
  • Access a wealth of external data from our Trend Cloud and/or other available data providers, including weather, macroeconomic indicators and events, to better understand causal factors and test new demand scenarios and sensitivities.
  • Digitally test what-if demand scenarios and sensitivities across time horizons. Probabilistic forecasting allows you to evaluate multiple demand scenarios to arm your planners with insights for faster, smarter decisions amidst changing conditions.
Learn more about Coupa Demand Modeling: Explore how advanced AI algorithms paired with an intelligent use of internal and external data can bring new context to demand across your enterprise.