Packaging Analytics in Singapore
Packaging plants know their material waste number at month-end. What they don't know is which machine, which shift, which substrate, which operator caused it — and that's the only version of the number you can act on.
Material consumption variance is the most under-tracked cost driver in packaging. Most plants only see it at month-end — after the waste has already happened. Singapore organisations operating across APAC face a specific challenge: the HQ analytics platform works well for Singapore. It doesn't work for the manufacturing plant in Johor or the distribution centre in Jakarta. Regional consolidation — pulling operational data from sites with different ERPs, different data quality levels, and different local reporting requirements — into a single APAC view is the most common project we run for Singapore-based organisations.
What we hear from operators
The problems we solve
These aren't hypothetical pain points assembled from industry reports. They're observations from actual plant floors, warehouse ops, and finance desks — written down because they come up in almost every first conversation.
Material variance is known monthly, not daily
Standard vs actual material consumption is reconciled in SAP at month-end. The number is reported. The head of operations reviews it. And then nothing changes because there's no way to trace it back to a specific machine run, a specific batch of substrate, or a specific operator. The variance is real. The cause is invisible. The month after, it happens again.
Machine OEE is inconsistent across lines
Some lines have automated OEE tracking from the machine controllers. Others rely on shift logs. Most packaging plants have a patchwork — some data is automated, some is manual, some doesn't exist. The result is an OEE number for the plant that's partly real and partly estimated, and nobody knows which parts are which.
Changeover time is tracked but not analysed
Changeover events are logged — start time, end time, SKU before, SKU after. But the data is almost never used to identify which changeover sequences are consistently slower, which lines have the most variation, or whether the standard changeover time in the production schedule reflects reality. It's data that exists and does nothing.
How we work
Our approach
01
Connect machine data to SAP production orders
We integrate machine controller data — OPC-UA, SCADA, or direct database if that's what's available — with SAP PP to create a linked record: this machine run, this production order, this material batch, this quantity consumed, this duration. The foundation that makes granular variance analysis possible.
02
Build machine-level OEE and material consumption dashboards
OEE by machine, by shift, by line — updated in real time or at 15-minute intervals. Material consumption vs standard by machine run. Changeover analysis showing actual vs standard by SKU transition. Scrap by cause code, connected to the machine and the substrate batch. Shift supervisors see what's happening before the shift ends.
03
Identify the specific waste drivers, not the aggregate number
Once the granular data is flowing, we build the analysis that identifies the 20% of SKUs, machines, or shift combinations responsible for 80% of material variance. That's the prioritised action list — not a general recommendation to reduce waste, but a specific list of machine settings, substrate suppliers, or changeover sequences that are driving the cost.
What changes
Outcomes
These are specific, measurable shifts — not benefit statements. Every outcome listed here has been achieved with a client.
Material variance visibility: monthly aggregate → machine-level daily tracking
Quality and production teams can trace a material variance event to the specific machine run within 24 hours of it occurring — not at month-end when the cause is already forgotten.
OEE accuracy: partly estimated → fully measured from machine data
Automated OEE collection replaces shift log estimates. The number becomes trustworthy enough to act on, and the line-by-line comparison reveals which equipment needs attention.
Changeover analysis: logged but ignored → optimised sequence scheduling
Changeover time analysis identifies the SKU transition sequences that consistently overrun. Scheduling adjustments based on actual changeover data reduce total changeover time across the plant.
Technology stack
Common questions
What buyers ask us
These are questions that come up in almost every first or second conversation. If yours isn't here, it will be in the first call.
Our machines are old and don't have modern connectivity. Can we still get this data?
Older machinery is common in packaging. Most machines — even those installed 15–20 years ago — have some form of signal output, even if it's just a cycle counter or a PLC with basic connectivity. We assess what's available machine by machine and design the integration accordingly. In some cases, a low-cost sensor retrofit is the right answer. We'll tell you honestly when that's needed.
We run many different SKUs with frequent changeovers. Does the data model handle that?
High SKU complexity and frequent changeovers are the norm in packaging. The data model handles it — each production run is tagged with the SKU, the packaging format, the substrate specification, and the changeover that preceded it. That's what makes it possible to identify which changeover transitions are consistently slow without averaging across all of them.
Who actually uses this — the shift supervisor or the plant manager?
Both, but differently. The shift supervisor needs the real-time view — what's running now, how it compares to standard, what exceptions need attention today. The plant manager needs the trended view — which lines are improving, where the variance is concentrating, what's the forecast for the month based on current performance. We build both. They use the same data at different levels of granularity.
Ready to move
Start with a conversation, not a proposal
First call is 45 minutes. No deck. We ask about your systems, your team, and your most pressing operational problem. You get a clear view of where the gap is and what closing it looks like. No obligation.