PartsOS Forecast
Haver & Boecker: AI-Powered Spare Parts Forecasting for 20,000 SKUs, Service-Driven
How the global machine builder is using PartsOS to move from reactive, manual inventory planning to AI-based demand forecasts and raise its service level.
Who is Haver & Boecker?
HAVER & BOECKER is a tradition-rich, family-run industrial company headquartered in Oelde (Westphalia, Germany), founded in 1887. Today, it ranks among the world's leading technology providers in wire mesh and machinery manufacturing, with subsidiaries across the globe. HAVER & BOECKER unites two core business areas under one roof:
🔹 Wire Weaving Division
🔹 Machinery Division
Within the Machinery Division, HAVER & BOECKER develops equipment for the filling, packaging, and logistics of bulk materials (e.g. cement, building materials, chemicals, food). These include filling machines, weighing and dosing systems, and complete packaging lines.
A critical part of this business: spare parts and service.
High machine availability: Spare parts are essential to prevent downtime and quickly restore production processes.
Long life cycles: Industrial equipment often runs for many years — reliable spare parts supply secures long-term operation.
Original parts & quality: Precise original spare parts ensure optimal performance, safety, and efficiency.
That makes spare parts supply a business foundation — for Haver & Boecker and for every one of their customers worldwide. Due to the high share of special-purpose machines and their long operational lifetimes, the spare parts portfolio is exceptionally broad: over 20,000 distinct items have been sold as spare parts over the past three years.
The Starting Point
Disposition across the entire portfolio runs on automated but rigid rules. Every item — spare part or production part — is treated the same way. There's no spare-parts-specific focus and no differentiated forecasting logic. Currently selected items are planned with the same method: a slightly adjusted average of consumption over the past 12 months.
In practice, this meant:
🔹 Reactive forecasts: Stock levels were based on the past 12 months of consumption.
🔹 20,000 SKUs, high complexity: A special-machine portfolio doesn't lend itself to standardization. Stocking decisions get made in bulk or have to be adjusted by hand — eating up coordination time.
🔹 Rigid disposition rules: Led to frequent small orders with process costs of around €100 per transaction.
🔹 Stock-out situations: Critical spare parts repeatedly missing, stretching lead times and causing delivery delays.
🔹 Limited stock range and shipping times: Customers are unhappy with delivery times, leading to lost sales — particularly on marketable items.
The result: a planning team forced to chase critical spare parts and constantly battle backlogs and stock-outs.
Why PartsCloud
Before the decision, Haver & Boecker deliberately weighed three alternatives:
PartsCloud won on three criteria:
-
AI- and ML-based forecasting, not 12-month logic
PartsOS doesn't just analyze the past — it detects seasonality, peaks, lifecycles, and consumption patterns, and can factor in Haver & Boecker's specific machine knowledge. Reactive planning becomes proactive, data-driven planning.
-
Integration, not replacement
PartsOS works as a standalone AI tool that complements the existing SAP setup. This keeps effort and IT risk low and delivers speed that an S/4HANA migration alone can't match.
-
Direct impact on every pain point at once
Service level up, process costs down, scrap down — and inventory built up exactly where it's missing today. Demand-based, not blanket. At the center: service level. It's Haver & Boecker's most important lever and the central target metric of the business case.
The Setup
The pilot started with 150 material numbers as initial scope.
The next step: a gradual expansion toward roughly 10% of the SKU portfolio — about 2,000 items — being loaded into PartsOS Planning and analyzed. In this phase, purchase requests are still deliberately handled manually by the planning team rather than triggered automatically.
Since calendar week 22, Haver & Boecker has been using PartsOS specifically for the most critical items — the spare parts that repeatedly arrived late or were unavailable in the past.
Running in parallel:
🔹 Data integration via structured Excel uploads as a pragmatic starting point ahead of a deeper SAP integration
🔹 Regular alignment meetings between the Haver & Boecker and PartsCloud teams to calibrate the forecasts and incorporate edge cases
🔹 A fundamental internal shift in the planning team: moving from rigid rules toward service-level-driven stocking. This is deliberately not just a tool topic — it's a mindset shift Haver & Boecker is actively driving.
What the Business Case shows
Before the pilot, PartsCloud and Haver & Boecker built a detailed business case together. The dimensions at full rollout:
15%
higher availability
< 6 months
payback period including peak phase
up to 1 Mio. €
ROI-amount per year
What's Next
🔹 Validation of the business case projections through the remainder of the pilot phase
🔹 Gradual expansion beyond the initial 150 items - full scale-up is tied to automated SAP connectivity for the demand forecasts
🔹 Deeper SAP integration ideally automated export of the forecasts as Planned Independent Requirements to eliminate manual transfer steps
🔹 Expansion to additional planning areas beyond the initial setup
🔹 Internal service-level discussion: higher stocking at strategic points as a deliberate investment in delivery capability
🔹 Handling of dual-use consumption: many items are needed both as spare parts and for new machines. PartsOS Planning needs to cleanly differentiate and reflect this in its forecasting logic.
The pace is set. Service means delivering. That's exactly what Haver & Boecker is now equipped to do — a little better, every day.
FAQs
-
What does Haver & Boecker use from PartsCloud?
Haver & Boecker uses PartsOS — PartsCloud's AI-based parts forecasting solution. The ongoing pilot currently covers 150 material numbers; the planned scaling targets ~10% of the SKU portfolio (about 2,000 items).
-
How does PartsOS integrate with Haver & Boecker's SAP environment?
During the pilot, via structured Excel uploads (data export from SAP, upload to PartsOS, transfer of purchase recommendations back into SAP). A deeper, automated integration is planned and necessary as the next step.
-
What alternatives did Haver & Boecker evaluate?
SAP S/4HANA as a future option, a custom in-house build, and other providers in the spare parts space. PartsCloud won because of its AI-based forecasting, fast integration with the existing SAP setup, and direct impact on every relevant pain point.
-
How fast is time-to-value?
Initial demand forecasts are available early in the pilot phase. The initial data load of 9 files takes about 1.5 hours. Scaling and integration happen iteratively.
More Customer Stories
Find out how other industrial companies have transformed their spare parts planning with PartsCloud.
Coperion
How Coperion used PartsOS to virtually eliminate impending stockouts on critical components, increase parts availability by over 15%, and achieve full ROI within just three months.
EUCO Rail AG
How EUCO Rail is transitioning, together with PartsCloud, from reactive, spreadsheet-based planning to proactive, AI-powered parts management, ensuring critical components are reliably available across all locations.