Forecast object
Event outcome: timing known, outcome uncertain.
Event timing: outcome known, timing uncertain.
Time series: historical observations projected into future periods.
Interactive forecasting guide
Forecasting IsNot One Formula
Level, trend, and seasonality are different demand structures. This guide keeps them separate, compares them only when useful, and follows the complete workflow from forecast definition and holdout evaluation to Excel, SAS, and cross-functional S&OP decisions.
Teaching schematicCalculated from included dataEditable and user-generatedRepresentative software output
Keyboard: Space play/pause, → step, R reset. The shortcuts are ignored while typing in a field.
Stable level
Variation around a roughly constant mean.
Trend
A persistent direction of change over time.
Seasonality
A recurring pattern tied to the calendar interval.
1 · Frame the problem before calculating
Forecast Object and Information Set
A method cannot be judged until the forecast object, users, horizon, aggregation level, data availability, and decision context are explicit.
Information set
Univariate: only the series’ own history.
Multivariate: adds predictors such as price, promotion, weather, or economic variables.
Forecast statement
Point: one number.
Range: an interval.
Density: a probability distribution. More information can support richer decisions, but is harder to communicate.
Define the forecast
2 · Identify the time-series structure
Three Patterns, Three Forecasting Problems
Moving averages and simple exponential smoothing are level methods. A trend requires an explicit trend component. Recurring calendar behavior requires a seasonal component. Treating all three as interchangeable creates systematic lag or repeated seasonal error.
Stable level: begin with a baseline
A naïve forecast is the minimum benchmark: next period equals the latest observed demand. A more complex process must beat a reasonable baseline to demonstrate value.
Level: average recent noise
A short moving average reacts quickly but remains noisy. A longer window is smoother but slower. Neither is designed to extrapolate a persistent trend.
Trend: watch a level model lag
Simple exponential smoothing can respond to change, especially with high alpha, but its multi-step forecast remains flat. A rising series therefore exposes the method’s structural mismatch.
Trend: estimate the slope explicitly
Time-series regression models demand as an intercept plus change per period. The slope extends the direction into the holdout horizon.
Seasonality: identify the repeating clock
Multiplicative seasonal indices measure demand relative to an estimated trend. Each month receives a factor above or below 1.0.
Level + trend + seasonality
Holt-Winters updates level, trend, and seasonal factors each period. It is not “better” by definition; it is appropriate only when those components are present and stable enough to extrapolate.
Calculated from included data
Stable level · Naïve baseline
Training actualHoldout actualFixed-origin forecastForecast origin
3 · Data workspace
Editable Monthly Demand Dataset
The included workbook has 60 monthly observations per series: 48 training periods and a 12-period holdout. Edit any observation or upload a CSV; all methods, metrics, charts, and exercises recalculate immediately.
Accepted: date,demand or date,level,trend,seasonality. Header names are case-insensitive. Comma, semicolon, and tab delimiters are supported. Include an optional partition column, or the last 20% becomes holdout.
4 · Calculate, animate, and compare
Forecasting Method Laboratory
Select a method, adjust its parameters, move the forecast origin, and reveal calculations period by period. The holdout evaluation always fits only the training data.
Calculated from included data
Calculated from included data
Formula and numerical substitution
Calculated from included data
Training residuals
Residual = actual − one-step forecast. Persistent same-sign errors indicate bias; patterns indicate structure the model has not captured.
Calculated from included data
Holdout metrics
Editable and user-generated
Spreadsheet-style calculation grid
Cells reveal in sequence as the origin moves. Excel formulas use the visible worksheet convention: column A = period, B = actual, C = forecast.
Reference equations
Complete smoothing equations
The laboratory uses the multiplicative seasonal form. The additive specification is included for comparison. Each equation also shows its equivalent error-correction form.
Double exponential smoothing
Triple exponential smoothing, multiplicative
Triple exponential smoothing, additive
Symbols. dt is actual demand; Lt is level; Tt is trend; St is the seasonal component; s is the number of periods in a season; α, β, and γ are smoothing constants between 0 and 1; Ft+1 is the one-period-ahead forecast.
5 · Build the forecast in a worksheet
Forecasting in Excel
Excel makes every forecasting step visible: generate a time series, build one-step forecasts, calculate errors, compare parameters, and preserve the logic in copy-down formulas.
Calculated from included data
Selected method in Excel
The compact equation shows the selected forecast operation. The worksheet expression updates with the method controls in the laboratory.
Forecasting workflow
Excel methods from data generation to seasonal regression
Follow the sequence when learning the methods, or open one step as a focused implementation reference.
Worksheet reference
Excel implementation notes
6 · Scale the same forecasting discipline
Forecasting in SAS
SAS separates data preparation from statistical procedures. A reliable workflow defines the time interval, fits competing models, creates a genuine forecast region, and compares every method on the same holdout observations.
Forecasting workflow
From an imported series to model selection
SAS Studio reference
Code examples
Instructional example only. The browser does not execute SAS. The performance summary below is calculated from the included or edited data.
Calculated from included data
Performance summary in a SAS-style table
7 · Evaluate honestly
Train, Holdout, Bias, Accuracy, and Error Structure
A low fitted error is not proof of future accuracy. All model rankings below use a fixed-origin forecast created from training observations only and compared with the separated holdout.
Core metrics and additional diagnostics
Error and performance formulas
MFE, MAD, MSE, and MAPE are the core forecast-quality measures. CFE, RMSE, tracking signal, and FVA extend the diagnosis. Here, n is the number of evaluated periods; error is actual minus forecast. MAPE is calculated as a ratio and displayed as a percentage.
Forecast error
Positive: underforecast. Negative: overforecast.
Cumulative forecast error (extension)
Running signed error; persistent drift signals bias.
Mean forecast error
Average signed error; a bias measure, not an accuracy measure.
Mean absolute deviation
Average error magnitude in the original demand units.
Mean squared error
Squares errors, so large misses receive more weight.
Root mean squared error (extension)
Returns squared-error performance to the original demand units.
Mean absolute percentage error
Undefined at zero actual demand and unstable when actual demand is near zero.
Tracking signal (extension)
Monitors cumulative signed error relative to typical absolute error.
MAD-based forecast value added (extension)
Positive: the new process step reduced error. Negative: it made the forecast worse.
Calculated from included data
Error-contribution heatmap
Teaching schematic
Why fitting and evaluation must be separated
Data leakage: using holdout observations to choose parameters or compute seasonal factors gives the model information that was unavailable at the forecast origin.
The workflow is: fit on training data → freeze the model → forecast the holdout → compare forecast with actual → select the method → refit the selected method on all known data for a future forecast.
Calculated from included data
Method-comparison scorecard
No universal winner is declared. Each column ranks a different objective. Rank 1 is best within that criterion and current dataset. Accuracy uses holdout RMSE; bias uses absolute holdout MFE; responsiveness compares forecast changes with actual holdout changes; stability uses the standard deviation of forecast changes; interpretability is an explicit teaching rubric rather than a statistical estimate.
8 · Parameter sensitivity
Responsiveness Versus Stability
A high alpha puts more weight on the newest observation. A longer moving-average window spreads weight over more periods. Both choices alter how quickly forecasts move and how much noise they transmit.
Alpha experiment
Moving-average window experiment
9 · Compare each process step with doing less
Forecast Value Added Ladder
Forecast Value Added asks whether a step improves performance relative to a prior baseline. Here, positive FVA means a reduction in holdout MAD relative to the previous step.
Calculated from included data
Naïve → statistical → judgmental adjustment
A judgmental override is not automatically value-adding. It must be evaluated against the unadjusted statistical forecast and the naïve baseline.
S&OP version rule: preserve the statistical forecast, commercial adjustment, constrained supply plan, approved consensus plan, and actual result as separate records. Use FVA for forecast changes; use service, cost, inventory, and financial measures for planning decisions.
10 · Select by structure and decision need
Model-Selection Decision Tree
This is a teaching guide, not an automated guarantee. Data quality, structural breaks, intermittent demand, causal information, and business loss still require judgment.
11 · Turn forecast evidence into coordinated action
From Forecast to Plan: S&OP
Sales and Operations Planning integrates demand, supply, and financial perspectives at an aggregate level. The forecast remains an evidence-based estimate; S&OP converts that evidence into an authorized plan without erasing the original baseline.
Decision chain
Statistical baselineA reproducible forecast and its uncertainty, produced before political or operational adjustments.
Unconstrained demandExpected market demand before supply constraints, informed by customers, promotions, launches, and market intelligence.
Constrained supplyFeasible output under labor, capacity, supplier, inventory, technology, and logistics limits.
Balanced S&OP planReconciled demand and supply scenarios with explicit gaps, trade-offs, and assumptions.
Financial reviewRevenue, margin, working-capital, service, and cost implications translated into one business view.
Executive decisionManagement authorizes the plan, resolves exceptions, assigns owners, and records decisions.
Aggregate plan and MPSMonthly product-family commitments are disaggregated into weekly or daily finished-goods schedules by SKU.
MRP and executionFinished-goods schedules drive time-phased raw-material, component, WIP, purchasing, and production actions.
The forecasting-to-execution handoff
Core distinction: an approved consensus plan may include capacity limits, targets, risk choices, and executive judgment. It should not be relabeled as an unbiased statistical forecast.
Cross-functional planning reference
Explore the S&OP decision system
Forecast
The most likely outcome under a stated information set and assumptions.
Target
The result management wants to achieve. A gap to forecast requires actions, not silent forecast inflation.
Plan
The actions, resources, timing, and ownership selected to respond to the forecast and pursue the target.
Constrained plan
The feasible commitment after capacity, supply, labor, inventory, capital, and logistics limits are applied.
What a healthy monthly package contains
- The untouched statistical baseline, current commercial forecast, and every documented override.
- Demand, supply, inventory, and capacity scenarios over a rolling 12–24 month horizon.
- New-product launches, delays, promotions, phase-outs, and SKU-rationalization exceptions.
- A financial bridge covering revenue, margin, operating cost, inventory, and cash.
- Decisions, owners, due dates, unresolved risks, and the prior month’s assumption misses.
What S&OP is not
- Not a meeting that averages conflicting forecasts until disagreement disappears.
- Not a substitute for an unbiased demand baseline or holdout evaluation.
- Not a daily SKU schedule, detailed machine schedule, or component purchase order.
- Not automatically successful because every function signed off on one number.
Planning level: S&OP typically works by product family, month, and aggregate resource category. MPS and MRP translate that decision into operating detail.
12 · Failure modes
Ten Common Forecasting and Planning Errors
Each error can invalidate a technically correct formula or turn a useful forecast into a poor operating decision.
1. Data leakage
Using holdout values, future promotions, or future seasonal ratios while fitting the model.
2. Incorrect time order
Sorting by demand instead of date, or reversing the series before applying lags.
3. Inconsistent intervals
Mixing daily, weekly, and monthly observations without aggregation rules.
4. Missing observations
Silently compressing the calendar so a two-month gap appears to be one period.
5. Inappropriate seasonality
Using season length 12 because the data are monthly without confirming a repeated annual pattern.
6. Overfitting
Selecting parameters on the same observations used to report performance.
7. Unexamined bias
Reporting MAD or RMSE while ignoring persistent underforecasting or overforecasting.
8. Metrics without context
Choosing a model by the smallest error without considering loss, horizon, responsiveness, stability, and operating consequences.
9. Forecast equals target
Raising the forecast to match an aspiration instead of preserving the baseline and specifying demand-shaping actions.
10. Lost version history
Overwriting the baseline with an override or constrained plan, making bias, accountability, and Forecast Value Added impossible to evaluate.
13 · Practice
Short Graded Exercises
Use the hints only after attempting the question. Worked solutions are concise and tied to the forecasting and planning conventions used throughout this guide.