AI Case Study
Big River Steel makes more accurate demand predictions using machine learning
Big River Steel has implemented Noodle.ai's enterprise AI solution aiming to optimise operations at the company's new metal recycling and steel production facility in Arkansas. Using machine learning models, the company is able to make demand predictions based on macroeconomic and historical data.
Mining And Metals
According to a Forbes contributor, Big River Steel leverages machine learning to accurately predict demand. "Big River succeeds by using capital wisely, so it needs to accurately predict demand for steel. To do so it employs machine learning models using macroeconomic data, historical demand for steel, manufacturing activity, and the activity of large consumers of steel (e.g., housing starts, oil rig counts)."
According to Business Wire: "Noodle.ai’s predictive AI engines, configured on its industrial operations platform, The BEAST, will help optimize a vast array of functions throughout the mill. 'This mill possesses a rich trove of sensor data for our platform to leverage, allowing us to help unlock breakthrough improvements in areas such as maintenance planning, production line scheduling, logistics operations, and environmental protection,' says Stephen Pratt, CEO of Noodle.ai."
"In January 2017, the mill’s first full month of production, Big River Steel established a record-setting month with over 63,000 tons of hot rolled steel produced during the month."
AI algorithms and machine learning models
"Steel mills built between the 1970s and 2010 handle their business on spreadsheets and laptops. But the operation of steel mills is just as dependent on math and metrics as any other business, and spreadsheets just can’t handle complex interrelated variables. Spreadsheets are also static in a very quickly changing business world.
According to Big River Steel’s CEO, David Stickler: 'We started by examining the financial spread between the price of scrap steel and finished steel. Many mill operators view scrap steel as a financial risk, we saw it as an opportunity – apply AI to improve profit per mill hour by starting at the very beginning of the process'."
"Macroeconomic data, historical demand for steel, manufacturing activity, and the activity of large consumers of steel (e.g., housing starts, oil rig counts)."