Supply Chain & Analytics
Forecasting
Forecasting attracts more sophistication than almost any other analytical problem and rewards it less reliably. Teams reach for gradient boosting and neural architectures on series where a seasonal naive method is within a couple of points, and the extra accuracy is consumed entirely by the maintenance burden of a model nobody fully understands.
The discipline that separates useful forecasting from expensive forecasting is unglamorous: benchmark against naive methods, backtest with proper temporal separation, measure accuracy at the level the decision is actually made, and be willing to conclude that the simple method wins. That conclusion is a good outcome and it is reported far less often than it occurs.
How the work runs
Four phases, and what comes out of each.
1–2 weeks
Establish the benchmark first
Before building anything we establish what naive methods achieve (last period, seasonal naive, moving average) at the level the decision is made. This is the bar. Roughly a third of forecasting engagements find the incumbent sophisticated model is not clearing it, which is worth knowing in the first fortnight rather than after a build.
Outputs
- Naive benchmark accuracy at the decision's level of granularity
- Current model performance measured against that benchmark
- Accuracy metric chosen to match the decision's cost asymmetry
2–3 weeks
Segment by what is actually forecastable
A portfolio contains series with entirely different characteristics (smooth and seasonal, intermittent, lumpy, new with no history) and one method applied across all of them is wrong for most. Intermittent demand in particular breaks standard methods badly and needs approaches built for it. We segment on demand pattern and set the achievable accuracy floor for each.
Outputs
- Segmentation by demand pattern with method assigned per segment
- Achievable accuracy floor per segment, the irreducible noise
- Series flagged as genuinely unforecastable, with the implication stated
3–5 weeks
Build and backtest without fooling yourself
Models are built per segment and evaluated on rolling-origin backtests that respect time order, with no information available at evaluation that would not have been available at the moment of forecasting. Leakage is the single most common reason a model that looked strong in development disappoints in production, and it is usually subtle.
Outputs
- Segment-appropriate models with rolling-origin backtests
- Explicit leakage audit of every feature
- Honest comparison against the naive benchmark, per segment
3–4 weeks
Deploy only what earns its place
Segments where the model beats the benchmark materially go to production, with monitoring for drift. Segments where it does not keep the simple method, and we say so plainly. We also measure forecast value-add on human overrides, which frequently shows that a meaningful share of manual adjustment makes the forecast worse and can simply be stopped.
Outputs
- Production deployment limited to segments where it is justified
- Drift monitoring with defined retraining triggers
- Forecast value-add measurement on human overrides
What good looks like
The ranges we design toward.
5–15 pts
Accuracy improvement
Typical MAPE gain where no segmented statistical baseline previously existed.
~⅓
Engagements where simple wins
Share in which a naive or classical method matches the sophisticated incumbent. Reported rather than buried.
20–40%
Harmful overrides
Share of manual adjustments that commonly degrade the statistical forecast, and can simply be stopped.
Deliverables
What you are left holding.
- 01Naive benchmark and current-model performance at the level decisions are made
- 02Segmentation with an appropriate method assigned to each demand pattern
- 03Rolling-origin backtests and a documented leakage audit
- 04Production models only where they beat the benchmark, with drift monitoring
- 05Forecast value-add measurement so override discipline becomes evidence-based
What an engagement looks like
A representative shape.
Illustrative. This is the shape of work in supply chain & analytics, not an account of a specific client. We do not publish named results, and we would be wary of a firm that publishes them without the client in the room.
12 weeks
- 01Situation
A consumer goods manufacturer was opening a third distribution centre on the strength of a regional sales forecast, with freight cost per unit rising and no cost-to-serve view below channel level.
- 02What we did
Reconstructed eighteen months of shipment data into a true origin–destination model, built cost-to-serve to customer level, and tested the proposed footprint against demand growth, rate shock and node-loss scenarios.
- 03Where it landed
The third site turned out to be robust only under the most optimistic growth case. Redrawing catchments and re-tendering two lanes captured most of the projected saving without the capital, and the site decision was deferred rather than cancelled.
Where this connects
Rarely a self-contained problem.
Questions
The ones we get asked.
Will machine learning beat our current statistical forecast?
Sometimes, in specific places. Machine learning genuinely outperforms classical methods where there is rich related history, promotional and price response to learn, or many series that can share strength. It underperforms on sparse data, short history, structural breaks and anything requiring causal reasoning about a situation with no precedent. The honest answer requires a backtest, and we would rather run one for a fortnight than assert either way.
Our demand is genuinely volatile. Is forecasting even worth it?
Partly, and this deserves a straight answer. Irreducible volatility is real and no method removes it. But it is routinely used to excuse avoidable error, wrong aggregation level, ignored promotions, unmodelled cannibalisation, methods unsuited to intermittent demand. We measure the achievable floor first. If your accuracy is already near it, the answer is not better forecasting but an operation designed to need less of it, which is a supply chain engagement rather than an analytics one.
What accuracy should we be targeting?
There is no universal number and any consultant quoting one without seeing your data should be treated with suspicion. Achievable accuracy is set by the underlying variability of your series. The right target is the measured floor for your portfolio plus a realistic improvement, which we establish in the first fortnight, not a benchmark borrowed from a different business.
Can you forecast for a product with no sales history?
Only by analogy, and the uncertainty is large. New product forecasting works by finding structurally similar historical launches and borrowing their shape, which is legitimate but should be presented as a range with explicit assumptions rather than a point estimate. The bigger win is usually designing the launch so it can respond quickly to early signal rather than committing hard to a forecast nobody can make well.
Insights
Related reading.
The bullwhip effect: why your demand signal lies
Factory schedules swing by forty per cent while end-consumer demand moves by five. Nobody is behaving irrationally. That is precisely the problem.
Multi-echelon inventory: beyond the safety stock formula
The standard safety stock formula is correct and it is answering a question nobody in a multi-tier network is actually asking.
Cost-to-serve: the analysis most companies skip
Most businesses know their gross margin by customer. Rather fewer know which customers are profitable, and the two lists differ more than anyone expects.
S&OP versus IBP: what actually changes
Most descriptions of the difference are vendor taxonomy. The distinction that matters is whether a trade-off gets settled by someone with the authority to settle it.
Why people systematically under-order high-margin products
The mathematics of a single-period stocking decision is a hundred years old and unambiguous. Experienced buyers still get it wrong in the same direction, every time.
Closely related
More on Supply Chain & Analytics →Decision Science
Allocation, scheduling and network problems solved properly, with the constraints that genuinely bind and a model you can interrogate.
Supply Chain & AnalyticsData Foundations
The unglamorous layer everything else rests on, pipelines, models, tests and lineage, scoped to a capability rather than to the whole enterprise.
Supply Chain & AnalyticsDemand & Inventory Planning
One demand number the business will commit to, and an inventory policy that follows from it rather than from a rule of thumb.
Start a conversation
Talk to us about forecasting.
Most useful first conversations are thirty minutes and involve no proposal. Describe the problem you are looking at and we will tell you honestly whether it is one we can help with.
Or write directly to hello@shyenova.com
