Wrangler Replenishes with Neural Networks

Wrangler (Greensboro, N.C.), a manufacturer of men's and boy's jeans, shirts and knitwear, has embarked on a reengineering effort to improve its total supply chain, which has achieved significantly positive results for both the company and its retail customers. The most visible benefits have been increased sales volumes, lower inventory investments and improved inventory turns for retail customers and for Wrangler. And much of its success can be attributed to the application of neural network technology.

On average, retailers participating in Wrangler's continuous replenishment program (CRP) have experienced a 20% annual increase in sales, according to Jeff Kernodle, Wrangler's vice president of replenishment. Moreover, inventory reductions have greatly improved inventory turns.

Wrangler's CRP has grown from a single test program with 18 retail stores in 1990 to over 7,000 stores, which represents over 50% of the company's business volume. Supply chain reengineering at Wrangler applies to keeping its customers in stock in the right stock-keeping units (SKUs). As part of that effort, Wrangler has invested in eliminating non-value-added activities and working smarter at each step of the supply chain, from production planning through manufacturing processes to distribution operations to final store delivery.

An important part of supply chain reengineering at Wrangler has been revamping product forecasting and production planning. By forecasting production needs more accurately, Wrangler will be able to maintain a high level of in-stock customer service while carrying less finished goods inventories.

Most consumer goods manufacturers have historically planned production based on forecasts of order demand, and Wrangler was no exception. The lack of accuracy of historical order demand was illustrated in Wrangler's initial CRP results. "Order demand had been inconsistent with how sizes were selling," explained Kernodle. "We needed a better way to drive size planning to meet our objectives."

To improve production planning and forecasting, Wrangler has recently begun using neural network forecasting technology. It generates forecasts based on consumer demand data, rather than retail buyers' orders, to drive production planning. "Many retail customers now share their advertising and promotion plans, so we can fine tune inventories and replenishment accordingly," Kernodle said.

This information is now combined with consumer sales information to feed a neural network-based forecasting model developed using SkuPlan from Neil Thall Associates (Atlanta, Ga.). Forecasts are created for each retail chain. The aggregate of those chain forecasts now drives Wrangler's production planning. Wrangler's manufacturing and sourcing are now matched up with actual consumer demand.

SkuPlan's causal forecasting goes beyond standard time series analysis of sales data to incorporate other factors or variables that can influence an organization's sales. Database mining techniques analyze the data patterns and develop custom models which apply to the unique data of retailing operations, merchandising programs and competitive environment.

Better forecasts based on consumer demand, improved manufacturing processes, major reductions in cycle times, reengineered distribution systems, and ongoing retail CRPs have all contributed to reduced inventory, lower costs, higher sales and improved profitability at Wrangler.

Click here to return to Table of Contents for the Intelligent Manufacturing November issue.