1. Overview: Sales Forecast vs. Demand Plan
Understanding the distinction between the Sales Forecasting module and the Demand Planning module — and how they work together.
One of the most important concepts in Confido is the difference between the Sales Forecast and the Demand Plan. These are two distinct but interconnected views of volume, built by different teams for different purposes. They should converge over time, but they will not always match — and understanding why is key to using both effectively.
1.1 The Sales Forecast (Sales Read)
The Sales Forecast is built by the commercial team — account managers, sales leaders, and trade planners. It is grounded in in-store consumer performance: what is scanning through the register, how many stores are carrying each item, and what lift promotions are generating.
The Sales Forecast is built bottom-up from:
A baseline consumption forecast (store counts × base velocity, by retailer and item)
Promotional lift layered on top of the baseline
New distribution opportunities (confirmed and unconfirmed)
Shippers, displays, and seasonal activities
A buy-in delay that lags consumption timing to estimated shipment timing
The output is what Confido calls a 'sales read' — a comprehensive view of expected volume from the bottom up, rooted in in-store signals. It flows into the Demand Planning workspace as an opinion line called the Sales Forecast.
1.2 The Demand Plan (Demand Forecast)
The Demand Plan is owned by the demand planning team. It starts from a different place — historical shipments to each customer, rather than consumer scan data — and is used to drive production planning, inventory management, and supply chain decisions.
The Demand Plan may:
Use the Sales Forecast as its base (especially for new items or new distribution where no shipment history exists)
Use a statistical model run on historical shipment data (for mature, steady-state customers)
Combine both — run a statistical baseline and layer on promotional and distribution intelligence from the sales team
Override either input where the demand planner has specific business context
The Demand Plan can be the final consensus number used for purchasing, production scheduling, and supply chain commitments. It is more precise in the near term and accounts for things the sales forecast cannot — like how much inventory the customer currently has on hand and when their next order is likely to arrive.
1.3 Why They Are Different
Important: The Sales Forecast and Demand Plan will often show different numbers — this is expected and correct. The Sales Forecast is consumption-based and smoothed; the Demand Plan is shipment-based and accounts for order timing, customer inventory levels, and short-term constraints. The goal is for them to converge over time, not to be identical at all times. |
Common reasons they diverge:
The Sales Forecast lags consumption to account for shipment timing, but the lag is an average — actual order timing varies by customer and DC
The Demand Plan incorporates current customer inventory on hand, which can accelerate or delay near-term orders
The Sales Forecast is built on consumption scan data; the Demand Plan is built on shipment actuals from your ERP
Demand planners may apply overrides, adjustments, or statistical corrections that the sales team is not aware of
2. The Demand Planning Workspace
How the workspace is organized, how to navigate it, and the key elements on screen.
The Demand Planning workspace is your day-to-day operating environment for building, reviewing, and refining the demand plan. It is separate from the Sales Forecasting module but connected to it — pulling in sales intelligence as an overlay while giving you your own tooling to run models, make adjustments, and track accuracy.
2.1 Hierarchy and Grouping
The workspace is fully flexible in how you organize and view the forecast. You can group by:
Channel → Demand Planning Group → Product Family → Item (most common default)
Item → Channel → Customer (useful when focusing on a specific product across all customers)
Location → Customer → Item (useful for brands with multiple ship-from locations)
The Demand Planning Group is Confido's concept for the ship-to customer or customer cluster. It can be one-to-one with a specific ship-to (e.g., a single distributor DC) or it can aggregate multiple ship-to locations into one group (e.g., an 'All Other Distributors' bucket for smaller accounts).
Forecasts are built and maintained at the item level, but edits and model changes can be made at any level in the hierarchy. When you make a change at a higher level (e.g., total Publix), Confido apportions the volume down to the underlying items based on their relative volume share over a configurable time horizon. When you make a change at the item level, it rolls back up automatically.
Note: The apportioning time horizon — the number of historical weeks used to calculate each item's share of total volume — is configurable. You can also set exceptions to the default rule at any level if needed. |
2.2 Units of Measure
The Demand Planning workspace defaults to cases, which is the most common unit for supply chain planning. However, the workspace is flexible and can be configured to display and edit in units, cases, or pounds depending on your business. Dollar views are also available for context, though editing is done in volume units.
The sales team may forecast in sell units (consumer units scanned at the register), while the demand plan operates in cases or pounds. Confido handles the conversion between these levels so that both teams are working with the same underlying data in their preferred unit of measure.
2.3 Planning Horizon and Fiscal Calendar
The planning horizon — how far forward the demand plan extends — is configurable. Most brands set a rolling 12 to 18-month horizon. You can also configure different forecast strategies for different time horizons (e.g., use the Sales Forecast for the next 12 months, then switch to a statistical model beyond that).
Confido supports custom fiscal calendars including 4-4-5, 13-period, and weekly structures. The workspace can display actuals and forecasts rolled up to periods, quarters, or any fiscal grouping your team uses for reporting and accountability.
Tip: If your team is held accountable at the period level but plans at the weekly level, you can configure the workspace to show weekly detail by default while also being able to roll up to period view for review meetings and reporting. |
3. Historical Shipments and Baselining
How Confido ingests your shipment history, baselines it, and prepares it for statistical forecasting.
The Demand Planning module starts with your historical shipments — not consumer scan data. These come from your ERP (NetSuite, SAP, Business Central, etc.) and are ingested at the customer, item, and location level on a weekly basis. Historical data (typically 2-3 years) is loaded during onboarding.
3.1 Shipment History Ingestion
Confido connects directly to your ERP to pull weekly shipment actuals by customer, item, and ship-from location. If you are mid-ERP transition or have imperfect historical data, Confido can supplement with a CSV upload of historical shipment files. The onboarding team will work with you to align on the best approach for your data situation.
Note: If your historical shipment data has data quality issues — e.g., missing ship dates, incorrect item codes, or gaps from a system transition — Confido can work around this during the data load. It is better to load imperfect history than to start with no history at all, as even partial data helps the statistical models. |
3.2 Automatic Baselining and Outlier Detection
Once shipment history is loaded, Confido runs an automatic baselining process. This strips out large deviations — promotional spikes, pipe fills for new distribution, supply constraints, or other one-off events — to give you a clean baseline that represents your steady-state shipment rate.
Confido is uniquely positioned to do this accurately because it has access to both your shipment history and your sales intelligence (POS data and promotional calendar). When it sees a large spike in shipments and finds a promotion running in the corresponding POS data the following week, it can automatically tag that spike as promotional rather than treating it as a genuine baseline shift.
Deviations can also be tagged manually if the automatic detection misses something or if the cause was internal (e.g., a supply constraint that caused a delayed order). Each tagged deviation can be labeled with a business reason so the history of what happened and why is preserved.
Tip: Taking time to review and clean up the baseline during onboarding pays dividends throughout the year. A well-baselined shipment history means statistical models run on it will be more accurate from day one, and you will have fewer recommendations to clean up as new data arrives. |
3.3 Item Proxy for New Products
For brand new items with no shipment history, the demand planner can designate a proxy item — an existing product with similar characteristics — and use its velocity patterns as a starting point. This is particularly useful when launching a new flavor or format of an existing product where historical performance of the existing SKU can inform the ramp expectations of the new one.
4. Forecast Models
The different forecasting methodologies available in the Demand Planning workspace and when to use each one.
At every level of the hierarchy — total customer, product family, or individual item — you choose which forecasting model to use as your base. The model can be different at every level and is saved as your configured strategy for that node in the hierarchy.
4.1 The Two Base Model Types
Model Type | How It Works |
Sales Forecast | Uses the Sales Forecast from the Sales Forecasting module as the base. Reflects consumption actuals and the commercial team's assumptions about promotions, new distribution, and lift. Best for new items, new customers, or situations where you want to fully align with the sales team's view. |
Statistical Forecast | Runs a model on your historical shipment data (baselined or raw) to project future shipments. Confido evaluates multiple models and suggests the best fit based on historical accuracy. Best for mature, steady-state customers with consistent shipment patterns. |
4.2 Statistical Model Options
When you select a statistical forecast, Confido evaluates several model types and recommends the best fit based on which would have been most accurate historically (lowest MAPE). You can accept the recommendation or manually select a specific model:
Best Fit — Confido selects the most accurate model for that customer/item automatically, applied at the item level within the customer
Moving Average — smooths out recent shipment trends; useful for steady, low-volatility customers
Single Exponential Smoothing — weights recent data more heavily; responsive to recent trends
Seasonal Naive — repeats last year's pattern; useful for highly seasonal businesses with predictable year-over-year patterns
Holt-Winters — handles both trend and seasonality; good for growing brands with seasonal patterns
Croston's Method — designed for intermittent or sporadic demand; good for slow-moving items
Markov Chain — probabilistic model; good for customers with variable order timing
For each model, Confido can display accuracy metrics including MAPE (Mean Absolute Percentage Error) and bias, so you can evaluate which model has performed best historically before committing to it.
4.3 Baselined vs. Raw Statistical Forecast
When running a statistical model, you have a choice of what data to run it on:
Recommended for most customers: Baselined shipments: Confido strips out the historical promotional spikes and outliers first, then runs the model on the smoothed baseline. The sales team's promotions and new distribution are then layered on top as explicit adjustments. This gives you the cleanest separation between base volume and event-driven volume.
Use selectively: Raw shipments: Confido runs the model on the actual historical data including all spikes. This means the model will try to predict future spikes based on historical patterns. Useful for customers where you do not have a reliable promotional calendar or where promotions are consistent and predictable year over year.
Tip: For most brands, the recommended approach is: baseline the shipments, use a statistical model for the base, and let the sales team's promotions and opportunities layer on top as adjustments. This gives demand planners visibility into exactly what is driving each component of the forecast. |
4.4 Setting and Saving Model Strategies
When you select a model at any level of the hierarchy, it is saved as your configured strategy for that node. The workspace always shows you which model is currently in use at the level you are viewing. If different items within a customer are using different models, the customer-level display will show 'Multiple Models.'
You can set rules to automate model selection over time. For example: 'Use the Sales Forecast for any customer or item with less than 4 months of shipment history, then automatically switch to the best-fit statistical model once that threshold is met.' This allows the demand plan to evolve naturally as your business matures without requiring manual intervention for every new item or customer.
5. Layering on Sales Intelligence
How promotions, new distribution, and other sales-side inputs flow into the demand plan as explicit adjustment layers.
One of the most powerful aspects of Confido's Demand Planning module is that it lives in the same system as the Sales Forecasting and TPM modules. This means sales intelligence — promotions, new distribution, pipe fills — flows through automatically as clearly labeled adjustment layers on top of your base forecast, rather than needing to be manually communicated or re-entered.
5.1 What Flows Through Automatically
When you are viewing a customer in the Demand Planning workspace, you will see the following clearly broken out as separate rows below the base forecast:
Promotional lifts — incremental volume from promotions the sales team has entered in the TPM module, with the timing, lift percentage, and product detail visible. You can click into any lift row to see which promotion is driving it and what assumptions the sales team made.
New distribution / pipe fills — when a sales person confirms new distribution or enters a distribution opportunity, the associated pipe fill (load-in quantity for initial inventory fill) appears as its own row on the demand plan, clearly labeled with the retailer and timing.
Distribution opportunities (unconfirmed) — volume from opportunities that have not yet been confirmed. These are toggleable — you can choose whether to include them, exclude them, or include them weighted by their likelihood percentage.
5.2 Adjusting Sales Intelligence in the Demand Plan
You are not locked into the sales team's assumptions. As a demand planner, you can:
Toggle individual promotions or opportunities on or off in the demand plan
Override the lift percentage the sales team entered — for example, if you believe a Publix BOGO will drive 50% lift rather than the 80% the account manager entered, you can adjust it down in the demand plan and leave a comment explaining your rationale
Accept or reject specific overlays at any level of the hierarchy
All adjustments you make are tracked with a comment history. You can leave a note alongside any change — for example, 'Reduced lift from 80% to 50% based on recent Publix bogo performance at this price point' — so there is a clear audit trail of why the demand plan differs from the sales forecast.
5.3 Controlling the Sales Intelligence Sync
By default, sales intelligence flows through from the Sales Forecasting module in near-real time. However, demand planners often want more control over when and how updates come through — particularly as the forecast approaches a lock date.
Confido gives you full control over the sync:
You can sync all sales intelligence at any time with a single action to get the latest view
You can turn off the automatic sync as you approach a lock, so no surprise changes come through
You can resync selectively — for example, accepting a change the sales team made to one specific customer or item without pulling in everything else
You can set a time boundary so that syncs only pull forward-looking data and do not retroactively change anything within a locked or committed window
Important: Lock the sales intelligence sync before finalizing the demand plan for a period. This ensures that last-minute changes by the sales team do not alter a forecast that the supply chain team is already acting on. You can always resync a specific item individually if a legitimate change needs to be incorporated. |
6. Customer Inventory Data
How Confido uses customer inventory levels to inform and gut-check the near-term demand plan.
One of the key limitations of a purely consumption-based sales forecast is that it does not account for how much inventory the customer already has on hand. A distributor sitting on 12 weeks of stock is unlikely to order next week — even if your consumption forecast says they should. The Demand Planning module addresses this by bringing in customer inventory data where it is available.
6.1 Where Inventory Data Comes From
Confido connects to customer portals (the same portals used for the accounting deductions workflow) to pull weekly inventory data for supported retailers and distributors. Where customers make this data available — such as UNFI, KeHE, Target, Kroger, and Walmart — Confido ingests it daily or weekly at the DC and item level.
Note: Inventory data availability varies by customer. Not all retailers or distributors make this data available through their portals. For customers where inventory data is not available, the demand plan relies solely on the forecast models and sales intelligence. |
6.2 How Inventory Data Is Used
Customer inventory data appears in the Demand Planning workspace as a row below the base forecast, showing:
Current inventory on hand — units or cases the customer has in their DC right now
Weeks on hand — current inventory divided by your forecasted consumption rate, giving a rolling view of how long their inventory will last
Target weeks on hand — you can configure a target for each customer or DC (e.g., 'we want UNFI to always be at 6 weeks on hand'). The system will flag in red/yellow/green when they are above or below target
This data is used as a gut-check on the near-term forecast. If UNFI is sitting at 12 weeks on hand and your forecast shows a large order arriving next week, that is a signal worth investigating. Conversely, if a customer is at 1 week on hand and you have a big promotion coming up, there may be a supply risk that the demand plan needs to flag.
6.3 Open Orders
In addition to inventory on hand, Confido can bring in your open orders from your ERP — purchase orders that have been placed by customers but not yet shipped. This gives additional visibility into near-term demand that is already committed and helps identify gaps between what is ordered and what the forecast projected.
Open orders can also surface unexpected new demand — for example, a customer who starts ordering an item that is not in the sales plan. Confido can flag situations where an open order arrives for a customer-item combination with no corresponding forecast, prompting the sales team to confirm whether this is planned volume and update the forecast accordingly.
7. Adjustments, Overrides, and Collaboration
How demand planners modify the forecast, leave audit trails, and collaborate with the sales team.
Beyond choosing a base model and toggling sales intelligence layers, demand planners have a full suite of tools for making adjustments to the demand plan at any level of granularity.
7.1 Types of Adjustments
Percentage adjustment — increase or decrease the forecast at any level by a percentage. For example, 'plus 20% for the next 4 weeks at Kroger for this item based on an expected surge from a circular ad.'
Fixed unit/case adjustment — add or subtract a specific quantity. For example, 'add 500 cases to the UNFI East DC in week 12 for a special event.'
Final override — replace the entire forecast for a specific node with a number you enter directly. Useful when you have very specific intelligence that overrides the model entirely.
Growth factor — apply a percentage multiplier that ramps up or stays flat over a defined period. Shared with the Sales Forecasting module (see the Sales Forecasting guide for full detail on growth factors).
7.2 Comments and Audit History
Every adjustment made in the Demand Planning workspace can be accompanied by a comment. You can also tag team members in comments to notify them of a change or ask for input. All comments and adjustments are saved with a timestamp and the name of the person who made them.
You can view the full adjustment history for any node in the hierarchy at any time. This is particularly useful for explaining forecast changes in S&OP meetings — you can always trace back exactly what changed, who made the change, and why.
Tip: Make it a habit to leave a comment on every material adjustment, especially ones that deviate significantly from the model or the sales forecast. This creates a searchable record of business decisions and makes handoffs to new team members much easier. |
7.3 Collaboration with the Sales Team
While the Demand Planning workspace is primarily owned by the demand planning team, there are structured ways for the sales team to collaborate without giving them edit access to the demand plan itself:
S&OP cycle workflows (covered in Section 9) allow demand planners to trigger review actions for sales team members
Comments and notifications can be sent to sales team members tagged in the workspace
Demand planners can share specific reports or views with the sales team for review without giving them write access
The most common collaboration point is around the sales intelligence layers. If a demand planner disagrees with a lift assumption or a pipe fill timing, they can adjust it in the demand plan and leave a comment for the sales owner to review. The sales team retains ownership of the Sales Forecast; the demand planner owns the final Demand Plan.
8. Versioning, Locking, and Forecast Accuracy
How to manage multiple forecast versions, lock forecasts for supply chain commitments, and measure accuracy over time.
A rigorous versioning and locking process is essential for running meaningful forecast accuracy reporting and for giving your supply chain team a stable number to plan against. Confido has a full suite of versioning tools designed to support standard S&OP and IBP cycles.
8.1 Scenarios and Versions
Confido supports multiple forecast versions simultaneously. You can create a new version by copying an existing one and giving it a name — for example, 'P6 Live,' 'P6 High Side,' or 'P6 Budget Comparison.' Each version is independent and can use different model configurations or adjustments.
Common uses for multiple versions:
A 'live' version that the demand team actively maintains and hands off to supply chain
A 'high side' scenario that includes all distribution opportunities at full likelihood, for capacity planning
A 'budget' version loaded at the start of the year for ongoing variance tracking
A 'sales forecast' version that represents the unadjusted sales team view, for comparison
Tip: Naming conventions matter. Use a consistent naming structure (e.g., 'P6 2026 — Live,' 'P6 2026 — High Side') so that versions are easily identifiable in reports and review meetings. |
8.2 Snapshotting for Accuracy Tracking
A snapshot is a point-in-time copy of a forecast version that is saved and locked — it cannot be edited after it is created. Snapshots are the foundation of forecast accuracy reporting.
The typical workflow for accuracy tracking:
At the end of each planning cycle (e.g., end of period), take a snapshot of the live forecast and name it (e.g., 'P6 2026 Locked — Apr 28')
This snapshot becomes your 'lag 1' forecast — the forecast that was in place one period before actuals arrived
You can also maintain 'lag 2' and 'lag 3' snapshots for brands that measure accuracy on a longer horizon
When actuals come in, reports automatically compare actual shipments to each historical snapshot at whatever level of granularity you need
Confido can also set up automated snapshots on a schedule — for example, automatically taking a snapshot every Friday at 6pm — so you always have a consistent lock point without relying on manual action.
8.3 Forecast Lock Windows
Many supply chain teams operate with a frozen forecast window — a period within which the forecast cannot change without going through a formal process (e.g., an abnormal demand form). Confido supports this through version control:
Snapshot the forecast at the start of the frozen window and mark it as the supply chain commitment
The 'live' forecast can continue to be updated, but supply chain works off the snapshotted version
Any changes made after the snapshot can be easily surfaced in a 'changes since last lock' report, showing what shifted and by how much
Demand planners can selectively accept specific changes into the live version without affecting the locked snapshot
Note: A locked snapshot does not prevent the live forecast from being updated. It simply preserves a point-in-time view that supply chain can act on with confidence, while the demand planning team continues to refine the forward-looking forecast. |
8.4 Forecast Accuracy Reporting
Confido's Omni-powered reporting layer lets you build fully customizable forecast accuracy dashboards. Common accuracy reports include:
Lag 2 accuracy by customer — how accurate was the forecast 2 periods ago compared to actual shipments that came in? Sortable by MAPE or raw unit variance
Biggest misses — a ranked list of the customer-item combinations with the largest absolute or percentage deviation between forecast and actuals, for the current period or rolling window
Accuracy trend over time — how is forecast accuracy improving or declining over rolling periods, by customer or total business
Model comparison — for customers where you are evaluating different statistical models, how does each model's historical accuracy compare to the sales forecast?
Reports can be configured to filter by any attribute — customer, channel, item, product family, US vs. Canada — and can be exported to Excel or scheduled for automatic email delivery to stakeholders who do not have direct Confido access.
9. S&OP Cycles and Workflow
How to use Confido's S&OP tooling to formalize the planning process, trigger reviews, and track progress.
For brands that run a formal Sales & Operations Planning (S&OP) or Integrated Business Planning (IBP) process, Confido has dedicated tooling to structure and manage the cycle. Even for brands that are earlier in their S&OP journey, this functionality can be used more informally as a monthly demand review workflow.
9.1 Kicking Off a Cycle
A new S&OP cycle is kicked off from within the Demand Planning workspace. When you start a cycle, you define:
The planning horizon to review — for example, 'review the next 3 periods of major activities'
What you want the sales team to do — confirm upcoming promotions are still happening and correctly timed, confirm new distribution opportunities are still on track, update store counts or timing if anything has changed
Deadlines for each action
Once the cycle is kicked off, the sales team receives notifications and a dedicated dashboard showing exactly what they need to review and by when. Progress is tracked in real time — the demand planning team can see at a glance how many promotions have been confirmed, how many opportunities are still pending, and where there are gaps.
9.2 What Sales Team Members See
During an active S&OP cycle, sales team members see a list of the specific items they need to take action on:
Promotions coming up in the review window that need confirmation — is this still happening? Is the timing right? Is the store count accurate?
Distribution opportunities in the pipeline — is this still on track? Has the reset date shifted? Has the store count changed?
They can confirm, adjust, or flag each item directly from their notification dashboard. Once confirmed, the update flows into the Demand Plan automatically as part of the controlled sync process.
9.3 Locking the Cycle
At the end of the review period, the cycle is closed and the demand plan is snapshotted. This becomes the locked forecast version that supply chain uses for the coming period. Version history shows which cycle each snapshot was associated with, creating a clear audit trail of when each forecast was finalized and what process was used to produce it.
Note: You do not need a fully formal S&OP process to benefit from cycle tooling. Even using it informally — as a monthly 'demand review' where you ask the sales team to confirm their big upcoming events — creates structure and accountability that significantly improves forecast accuracy over time. |
10. Reporting and Data Export
How to get data out of the Demand Planning module and build the reports your team needs.
The Demand Planning module uses Omni — an embedded reporting and analytics layer — to power fully customizable dashboards and reports. Every data point in the workspace is available for reporting: historical actuals, forecast versions, snapshots, sales forecast, statistical models, adjustments, and customer inventory levels.
10.1 Building Custom Dashboards
During onboarding, the Confido team works with you to understand what reports you need and helps configure your initial dashboard. From there, your team has the tooling to create and modify reports yourselves. Common views include:
Forecast vs. actuals table, sortable by largest miss, filterable by customer or item
Lag 2 and lag 3 accuracy tracking with MAPE and bias
Version comparison — live forecast vs. locked snapshot vs. budget, side by side
Biggest changes since last lock — ranked list of what shifted and by how much
Customer inventory weeks on hand — current status across all customers with inventory data
Promotion performance — planned lift vs. actual lift by promotion and retailer
10.2 Scheduled Reports and Alerts
Reports can be configured to run on a schedule and be delivered automatically via email — even to stakeholders who do not have Confido access. Common scheduled reports include:
Weekly forecast accuracy digest — sent to the demand planning team every Monday showing the prior week's biggest deviations
Monthly S&OP summary — sent to supply chain and finance leadership ahead of the monthly review meeting
Exception alerts — triggered when a specific threshold is breached, such as a customer whose weeks on hand drops below 2 weeks or a forecast change above a defined percentage
10.3 Exporting Forecast Data
The final demand plan — including all layers and adjustments — can be exported from the workspace in several ways:
Direct export to Excel or CSV from within the workspace, with configurable columns and row groupings
Automated feed to a data warehouse (e.g., Snowflake, Google BigQuery) for brands with a data infrastructure
Direct integration to your ERP or planning system (e.g., SAP APO/IBP, NetSuite) where the integration has been configured during onboarding
The export includes item codes, customer identifiers, weekly quantities in your configured unit of measure, and any other fields needed to feed downstream planning systems. Confido works with each brand during onboarding to configure the export format to match what their supply chain or ERP team needs.
11. Frequently Asked Questions
Common questions from demand planners, supply chain teams, and finance leaders.
Q: Do I have to manually update the forecast for every customer and item? A: No. Confido generates forecasts automatically for all customers and items based on your configured model (sales forecast or best-fit statistical model). Your role as a demand planner is to review exceptions, refine models where needed, and apply targeted overrides — not to manually enter forecasts row by row. The system handles the heavy lifting; you handle the judgment calls. |
Q: How much shipment history do I need to run a statistical model? A: Generally, at least 4 months of clean shipment history is enough to start running basic statistical models. More history (12-24 months) gives better seasonal pickup and more reliable model selection. For new items or new customers with no history, use the Sales Forecast as your base until enough shipment history accumulates to switch to a statistical model. |
Q: Can I use different models for different customers? A: Yes — and this is by design. The model is configured independently at every level of the hierarchy. A common approach is to use the Sales Forecast for newer customers and items, and statistical models for mature, steady-state accounts. You can also set rules to automatically switch a customer from Sales Forecast to best-fit statistical once a minimum history threshold is met. |
Q: If a salesperson changes a promotion after I've locked the forecast, will it affect my demand plan? A: Only if you allow it to. You control the sync between the sales forecast and the demand plan. Before locking, you can turn off the automatic sync so no changes flow through. If a specific change needs to be incorporated after a lock, you can resync that one customer or item individually without affecting anything else. |
Q: How does Confido handle Costco-style rotation business where the commitment is a total quantity rather than a weekly rate? A: Confido supports a 'committed orders' concept for customers like Costco where you are working toward a fixed total quantity commitment rather than a steady weekly shipment rate. For the near-term active rotation, you can firm up specific quantities and timing directly in the demand plan. For the longer horizon, you can use consumption-based assumptions (warehouse count × average velocity) as a proxy once the near-term rotation is complete. |
Q: Can we load a budget or AOP into Confido for comparison? A: Yes. A budget or AOP can be loaded as a separate forecast version at whatever level of granularity you have it (customer, item, total business). Once loaded, it appears as a comparison line in the reporting layer, so you can see live forecast vs. budget side by side and track variance over time. |
Q: How do we handle price changes that are expected to affect volume? A: You can apply a growth factor (which can also model decline) at any level to account for expected volume changes due to a price increase or decrease. For example, you could apply a -4% multiplier starting from the effective date of a price increase, scoped to specific items or channels. As actuals come in after the price change, the recommendations system will flag whether your volume assumption was accurate and help you refine it. |
Q: Can the demand plan be fed directly into SAP or another ERP for production planning? A: Yes, though the specific integration depends on your ERP setup. Confido can export the demand plan in a format compatible with your downstream system, feed it to a data warehouse for onward processing, or — where a direct integration has been configured — push it automatically to your ERP. The onboarding team will work with you to define the right export format and process for your supply chain workflow. |
Confido Demand Planning Module — Internal Reference
For questions, contact your Confido onboarding team.