Ford Wins 2013 INFORMS Prize for Company-Wide Efforts in Analytics and Data Science
DEARBORN, MI--April 8, 2013:
- Institute for Operations Research and the Management Sciences recognizes Ford efforts to use data to run a smarter business and build better products
- Ford has been using business analytics and data-driven decision making for more than 60 years
Ford Motor Company†today received the 2013 INFORMS Prize from the Institute for Operations Research and the Management Sciences. The award recognizes Ford's long-running, company-wide effort to use data science and predictive analytics to improve overall operations and performance.
Applying rigorous analytics, including machine learning, operations research, data mining and big data throughout the business has played a key role in the resurgence of Ford in the past seven years. When chief executive officer Alan Mulally came to Ford in 2006, he helped to expand and institutionalize data-driven decision making throughout all aspects of the company.
"Analytics and operations research was a major enabler of our turnaround and our ongoing success as a data-driven company," said Bob Shanks, Ford Motor Company executive vice president and chief financial officer. "Receiving the INFORMS Prize is recognition of the significant role and impact of analytics at Ford."
A long history of data
Operations research and statistical control have a long history at Ford, dating back to just after World War II when Henry Ford II hired 10 young veterans of the U.S. Army Air Force's Statistical Control Command. The group became known as the "Whiz Kids" and included Charles "Tex" Thornton, who founded Litton Industries; Robert McNamara, who rose to president of Ford before serving as U.S. Secretary of Defense under President John F. Kennedy; and J. "Ed" Lundy, who eventually became Ford's chief financial officer. The team brought the lessons of organizing wartime logistics for the United States military to the problems of running a huge manufacturing enterprise.
In the early 1980s Ford again took a leadership position in American industry as one of the first U.S. companies to implement statistical process control methods pioneered by W. Edwards Deming.
"We continue to build on our history of data-driven decision making," said John Ginder, manager, systems analytics and environmental sciences in Ford's Research and Innovation group. "Throughout the company, we're using data science to create smarter business strategies, make better product decisions, assist dealers to be more successful, and improve customer satisfaction."
Centers of excellence
Analytics is used widely in diverse applications at Ford, including research, product development, manufacturing, supply chain, marketing and sales, finance, purchasing, information technology, and human resources.
Ford Motor Credit Company, the financing subsidiary of Ford, houses a major center of excellence in analytics. The Global Analytics team, established 20 years ago, developed proprietary scorecards to facilitate consumer and dealer lending and effective account management, and provides sophisticated analysis to support other areas of the business.
The Ford Marketing, Sales and Service Global Lifecycle Analytics team developed a range of models that help determine how to distribute cars to dealers and fleets, establish pricing and project residual values.
The Systems Analytics and Environmental Sciences group within Ford Research and Advanced Engineering harnesses the power of super-computing and advanced mathematics to mine big data, model market trends and optimize decisions.
In the U.S. market more than 90 percent of vehicle sales come from dealer stock and costs for carrying that inventory can often add up significantly. That makes it critically important for dealers to maintain the right mix of vehicles to maximize sales. Ford's Smart Inventory Management System, known as SIMS, analyzes historical sales and inventory data to generate recommended orders for dealers based on projected future inventory levels and targets.
Just as maintaining inventory is a major expense for dealers, stocking large quantities of parts is costly for factories. Just-in-time delivery of parts to assembly plants dramatically reduces manufacturing costs, and is one example of how Ford has used analytics to improve many facets of the production process, from the plant floor to component and vehicle logistics.
Ford developed the Just-in-time Execution & Distribution Information system, or JEDI, to help schedule the production and delivery of body panels from stamping plants to assembly facilities when they are needed. This minimizes premium shipping and overtime expenses when there is a mismatch between supply and demand for parts.
Optimization models developed at Ford also have helped the company understand projected consumer demands for fuel efficiency and mandated reductions in CO2 emissions. "Working with these models has helped us shape our Blueprint for Sustainability and determine where to focus our engineering resources for the most impact," Ginder said.
One component of the Blueprint for Sustainability, the overarching framework that guides Ford's product, operational and social sustainability planning, is its CO2 stabilization target glidepath. Ford calculated the glidepath required to meet future CO2 emissions targets and projected the costs for various technologies ‚€“ including diesel, hybrid and plug-in electric and hydrogen fuel cells ‚€“ over the next two decades, then developed a strategy to meet those targets. In the near term, reducing weight and downsizing engines provides the biggest overall impact on CO2 emissions for the most customers at the best value. The data suggest that as technology improves and costs come down over time, consumer interest is likely to shift more toward plug-in electric vehicles and potentially hydrogen fuel cells.
In recent years Ford's analytics initiatives have begun to incorporate big data and apply them to developing new vehicles.
"Social media and the vast amount of online conversation is helping us get a faster and more specific data set to help us make product decisions. We now use text-mining algorithms to formulate a more complete picture of what consumers want that is not available using traditional market research," said Michael Cavaretta, Ford technical leader for predictive analytics and data mining.
While developing the all-new 2013 Ford Escape, the vehicle engineering team made tens of thousands of decisions such as determining the liftgate configuration. Extensive analysis of customer satisfaction data was used to decide whether to retain the flip-glass system from the previous-generation Escape, adopt a power liftgate, or both.
"The picture that emerged was a four-to-one preference for power liftgates that could open and close with the touch of a button," added Cavaretta. "The result was a design that provided improved customer satisfaction while reducing manufacturing complexity and cost."