From Demand Forecast to Capacity Plan: A Five-Plant Study
From Demand Forecast to Capacity Plan: A Five-Plant Study
Research across five manufacturing plants tested whether leading-indicator forecasts improve capacity decisions, service levels and inventory—not just accuracy scores.
Research across five manufacturing plants tested whether leading-indicator forecasts improve capacity decisions, service levels and inventory—not just accuracy scores.
Planning & Budgeting
Why a forecast becomes a capacity decision
A manufacturer must decide how much to produce at each plant before demand is known. If planned output is too low, service levels can suffer; if it is too high, inventory and holding costs rise. This study asks whether external economic information helps those mid-term decisions.
How the five-plant case was evaluated
The researchers used monthly sales data from five plants of a global tire manufacturer and compared models with leading macroeconomic indicators against established extrapolative forecasts. They evaluated forecast accuracy and uncertainty, then simulated inventory and capacity consequences—including target service levels, holding costs and stockouts.
A capacity decision depends on timing
Imagine a plant manager needs to decide several months ahead whether to add an extra shift. Starting too early can leave staff and equipment underused. Starting too late can create backlogs. A forecast that gives earlier notice of a sustained change in demand may affect the decision even when the estimated size of the change remains uncertain.
Test the decision under realistic constraints
A useful capacity test starts with the actions the plant can actually take, the notice it needs, and the consequences of getting the decision wrong. It can then compare how the same decision rule would behave under different forecasts. Results will depend on the plant’s costs, capacity constraints and service targets, so the five-plant study is best read as an example of how to evaluate the decision.
What the researchers found
The paper reports that leading-indicator models were beneficial in this case and outperformed established extrapolative forecasts. Its key point is that the most accurate statistical forecast is not automatically the best capacity decision: the cost of excess stock and the cost of shortages both matter.
The implication for Morrow users
Use an indicator-informed forecast as an input to planning conversations about production, inventory and capacity—not as an automatic instruction to expand a plant. Morrow can make external signals visible and accessible, but the operational result depends on each company’s constraints, service targets and validation. The published outcome is the study’s, not a Morrow performance claim.
Want to know whether external indicators can improve your company’s forecast?
Want to know whether external indicators can improve your company’s forecast?
More to Discover
From Demand Forecast to Capacity Plan: A Five-Plant Study
From Demand Forecast to Capacity Plan: A Five-Plant Study
Research across five manufacturing plants tested whether leading-indicator forecasts improve capacity decisions, service levels and inventory—not just accuracy scores.
Research across five manufacturing plants tested whether leading-indicator forecasts improve capacity decisions, service levels and inventory—not just accuracy scores.
Planning & Budgeting
Why a forecast becomes a capacity decision
A manufacturer must decide how much to produce at each plant before demand is known. If planned output is too low, service levels can suffer; if it is too high, inventory and holding costs rise. This study asks whether external economic information helps those mid-term decisions.
How the five-plant case was evaluated
The researchers used monthly sales data from five plants of a global tire manufacturer and compared models with leading macroeconomic indicators against established extrapolative forecasts. They evaluated forecast accuracy and uncertainty, then simulated inventory and capacity consequences—including target service levels, holding costs and stockouts.
A capacity decision depends on timing
Imagine a plant manager needs to decide several months ahead whether to add an extra shift. Starting too early can leave staff and equipment underused. Starting too late can create backlogs. A forecast that gives earlier notice of a sustained change in demand may affect the decision even when the estimated size of the change remains uncertain.
Test the decision under realistic constraints
A useful capacity test starts with the actions the plant can actually take, the notice it needs, and the consequences of getting the decision wrong. It can then compare how the same decision rule would behave under different forecasts. Results will depend on the plant’s costs, capacity constraints and service targets, so the five-plant study is best read as an example of how to evaluate the decision.
What the researchers found
The paper reports that leading-indicator models were beneficial in this case and outperformed established extrapolative forecasts. Its key point is that the most accurate statistical forecast is not automatically the best capacity decision: the cost of excess stock and the cost of shortages both matter.
The implication for Morrow users
Use an indicator-informed forecast as an input to planning conversations about production, inventory and capacity—not as an automatic instruction to expand a plant. Morrow can make external signals visible and accessible, but the operational result depends on each company’s constraints, service targets and validation. The published outcome is the study’s, not a Morrow performance claim.
Want to know whether external indicators can improve your company’s forecast?
Want to know whether external indicators can improve your company’s forecast?
More to Discover
From Demand Forecast to Capacity Plan: A Five-Plant Study
From Demand Forecast to Capacity Plan: A Five-Plant Study
Research across five manufacturing plants tested whether leading-indicator forecasts improve capacity decisions, service levels and inventory—not just accuracy scores.
Research across five manufacturing plants tested whether leading-indicator forecasts improve capacity decisions, service levels and inventory—not just accuracy scores.
Planning & Budgeting
Why a forecast becomes a capacity decision
A manufacturer must decide how much to produce at each plant before demand is known. If planned output is too low, service levels can suffer; if it is too high, inventory and holding costs rise. This study asks whether external economic information helps those mid-term decisions.
How the five-plant case was evaluated
The researchers used monthly sales data from five plants of a global tire manufacturer and compared models with leading macroeconomic indicators against established extrapolative forecasts. They evaluated forecast accuracy and uncertainty, then simulated inventory and capacity consequences—including target service levels, holding costs and stockouts.
A capacity decision depends on timing
Imagine a plant manager needs to decide several months ahead whether to add an extra shift. Starting too early can leave staff and equipment underused. Starting too late can create backlogs. A forecast that gives earlier notice of a sustained change in demand may affect the decision even when the estimated size of the change remains uncertain.
Test the decision under realistic constraints
A useful capacity test starts with the actions the plant can actually take, the notice it needs, and the consequences of getting the decision wrong. It can then compare how the same decision rule would behave under different forecasts. Results will depend on the plant’s costs, capacity constraints and service targets, so the five-plant study is best read as an example of how to evaluate the decision.
What the researchers found
The paper reports that leading-indicator models were beneficial in this case and outperformed established extrapolative forecasts. Its key point is that the most accurate statistical forecast is not automatically the best capacity decision: the cost of excess stock and the cost of shortages both matter.
The implication for Morrow users
Use an indicator-informed forecast as an input to planning conversations about production, inventory and capacity—not as an automatic instruction to expand a plant. Morrow can make external signals visible and accessible, but the operational result depends on each company’s constraints, service targets and validation. The published outcome is the study’s, not a Morrow performance claim.