The Missing Demand Signals for Improving Supply Chain Forecasting and Production Planning

Visibility is the foundation of effective demand forecasting and production planning. Manufacturers can only plan for the demand they can see, and supply chain and production teams often lack early insight into the specific configurations, features, and option combinations customers are requesting. Without that level of visibility, supply chain teams may miss emerging demand patterns, inventory risks, and component dependencies that directly impact service levels and profitability. 

Currently, 50% of manufacturers report that they’re able to track demand forecasting and inventory planning. However, only 45% track configuration decisions made before the order, and 30% or less track feature and option demand or the most or least quoted configurations. It’s an overlooked layer of data that can increase efficiency much earlier for high-mix, low-volume production.  

The limits of traditional forecasting models 

Traditional demand forecasting and production planning looks to historical orders to understand future demand. While it’s a reliable source of information, it only provides information after the order is made, rather than emerging demand trends that can improve lead times and margin.  

How can supply chains forecast demand for configurable products? 

Highly configurable products make production planning even more challenging. Supply chain and operations leaders must account for thousands or millions of possible combinations, constant changes in customer requirements, and regional and customer-specific preferences against a growing portfolio.  

Supply chains forecast demand for configurable products most effectively when they combine historical order data with configuration, quote, and feature-level demand signals. 

Quote activity helps supply chain teams identify growing feature demand and potential component constraints weeks or months before those changes appear in order history or a manufacturing Bill of Materials. 

Configuration-level insight helps answer: 

• Which options are appearing more frequently in quotes?  

• Which premium configurations are gaining traction but haven’t yet converted to orders?  

• Which feature combinations are being evaluated by customers?  

• Which regional preferences are emerging?  

• Which products are being configured but abandoned?  

• Which new product variants are generating interest? 

• Which product variants are increasingly bought or combined together? 

Those insights can significantly improve forecasting, inventory planning, supplier collaboration, and production scheduling. 

Why configuration decisions matter for supply chain leaders 

Imagine you’re selling commercial HVAC systems. 

Your forecast accurately predicts demand for 1,000 units next quarter. Inventory levels are healthy, and procurement has ordered components based on historical demand patterns. Yet production delays begin to increase. 

Looking at order volumes alone, demand appears stable. But configuration-level analysis reveals something important: 

• Customers are increasingly pairing a premium control system with a high-efficiency compressor package.  

• When those options are selected together, they require a specialized circuit board sourced from a supplier with a 16-week lead time.  

• The circuit board isn’t a problem when the options are ordered separately. It becomes a bottleneck when the combination becomes more popular.  

• Quote activity shows this combination appearing in nearly twice as many opportunities as six months ago, but supply chain teams weren’t tracking configuration trends closely enough to spot the shift.  

The manufacturer forecasted how many HVAC systems customers would buy. They didn’t understand how customer preferences were changing within those systems. They couldn’t see that six months before orders increased, the premium control system and high-efficiency compressor package began appearing together in a growing percentage of quotes. 

As a result, a single constrained component delayed production. Inventory accumulated for components associated with declining configurations. Procurement reacted after shortages appeared rather than planning ahead. Delivery commitments became harder to meet.  

How to improve demand forecasting accuracy

If you want to improve forecasting accuracy, start by looking beyond completed orders. Earlier demand signals, such as the decisions made during the sales configuration and quoting process, provide insights into customer preferences before they affect inventory, procurement, and production planning, giving teams more time to make better decisions and see potential risks.

1. Connect commercial and operational data

Improving demand forecasting starts with connecting data across the customer journey, not only in orders, but also quotes, configuration decisions, inventory, and production data. Just as the quoting process should have manufacturability embedded in configuration constraints, the quoting process should also provide downstream manufacturing teams with important quote and configuration data. This provides visibility into changing customer preferences before they affect procurement and production schedules.

2. Track demand at the configuration level

Only 27% of manufacturers can track metrics such as most quoted configurations, fastest-growing options, and feature adoption trends to identify shifts earlier. Embedded analytics that contextualize your CPQ data can show you which configurations require longer sales cycles or what is explored but doesn’t often convert. 

3. Measure business impact, not just demand

Not all demand contributes equally to profitability. Analyze which configurations generate the highest revenue, margins, and conversion rates alongside which products create the most operational complexity. This helps align supply chain investments with business outcomes. 

4. Identify emerging supply chain risks 

Look for demand patterns that could create future constraints. Which growing configurations rely on long lead-time components? Which option combinations require specialized resources? Understanding these relationships helps teams anticipate bottlenecks before they impact delivery performance.

5. Continuously refine forecasts with performance data

Demand forecasting should be an ongoing process. Regularly review metrics such as quote-to-order conversion rates, feature and option demand trends, most and least quoted configurations, and forecast accuracy. These insights help you improve planning decisions while balancing inventory, capacity, and profitability. 

Demand Forecasting for Manufacturing 4.0: From Product Forecasts to Configuration Intelligence 

Demand forecasting in manufacturing is evolving from product-level forecasting to configuration intelligence. Manufacturers that incorporate configuration, feature, option, and quote data into forecasting processes gain earlier visibility into demand shifts and can make more informed inventory, procurement, and production decisions. 

Manufacturers need configuration-level demand intelligence, because historical order data doesn’t reveal the full picture of emerging customer preferences, future component demand, or changing configuration trends. 

Learn how manufacturing leaders are forecasting today in our State of Manufacturing Report and discover how Tacton helps manufacturers turn configuration and quote data into actionable forecasting and planning insights.