Demand forecasting
without the complexity.
Fewer stockouts. Less excess inventory. No Excel acrobatics or data science team required.
- Automatic model selection for every SKU
- Accurate forecasts with confidence intervals
- Every forecast validated with backtesting and clear explanations
Now in pilot with supply chain planners
Forecast & risk
MAPE (backtest)
8.2%
Bias (backtest)
−1.3%
Forecast horizon
26 weeks
Last updated
today
Backtesting as standard
Every forecast validated with out-of-sample backtesting.
Automatic model selection
The best model for every SKU, no manual work.
Forecast intervals
P10–P90 intervals for better decisions.
Made for planners
Clear explanations in your language. No black box.
How it works
From CSV to defensible forecast in 3 steps
01
Upload
Upload your CSV with demand history. Intermittent patterns? No problem.
Drop your CSV here or click to upload
02
Compare
FlowForecast tests multiple models and automatically picks the best one.
03
Understand
Get your forecast with intervals, backtesting, and clear explanations.
Product
See FlowForecast in action
One overview with clear forecasts, risks, and recommendations. Everything you need to plan with confidence.
- Interactive forecast charts
- Confidence intervals (P10–P90)
- Risk signals & recommendations
- Winning models with explanations
- Backtest metrics per SKU
Forecast & risk
Insights
- Demand is expected to stay stable over the next 26 periods.
- Forecast confidence is medium (65%).
- 5 demand anomalies detected (2 high severity).
- Recommended action: increase stock.
Generated from your forecast data.
Winning model & why
ETS
Why this model?
- Demand profile: Smooth
- Exponential smoothing with automatically selected trend and seasonality.
Risk simulation
Probability of lost sales and inventory risk, simulated across thousands of demand scenarios.
Business impact
See what a risk means for revenue, working capital, and potential lost sales per product.
Why FlowForecast
More than a forecast
Everything you need to make better planning decisions.
Clear explanations
Understand detected seasonality, trends, and anomalies in plain language.
Automatic model selection
The best model for every SKU — ETS, Croston, TSB, Seasonal Naive, and more.
Backtesting as standard
Every forecast validated with out-of-sample backtesting and transparent metrics.
Intermittent demand
Purpose-built for lumpy and sparse demand patterns.
Seasonality detection
Detects and models seasonal patterns automatically where relevant.
Scenario insight
Simulate different demand scenarios and see the impact on inventory and service.
Simple, transparent pricing
Start free with single-series forecasting. Upgrade when your team needs batch processing and advanced features.
Questions planners ask us
How much history do I need?
Twelve months of weekly data is a good baseline — enough to detect yearly seasonality. With less, FlowForecast still produces a forecast and tells you which patterns it can't validate yet.
Where does my data go?
Your upload is used to compute your forecasts — nothing else. It is never used to train models and never shared. Our infrastructure runs in the EU (Frankfurt). Details are in the Privacy Policy.
We plan in Excel today. How does this fit?
Keep Excel for what it's good at. FlowForecast replaces the fragile forecasting part: upload your history, take the validated forecast back as CSV, and keep your downstream planning sheets.
Which forecasting models are used?
Proven statistical methods: ETS (exponential smoothing) for trended and seasonal series, Croston and TSB for intermittent demand, seasonal naive as the baseline to beat. The winner is chosen by backtest accuracy.
Do I need a data scientist to use it?
No. It's built so a demand planner can do this alone: upload, review the explanation, export. If you do have a data team, the backtest metrics give them everything they need to audit the results.
What makes FlowForecast different?
No black box. Proven statistical models, validated out-of-sample, with an explanation behind every number. Built for planners rather than data scientists — and it works alongside your existing Excel process instead of replacing it.
See your own data forecasted
Send us a message and we'll set you up in the beta.