Revenue Forecasting
Fload projects your app's future performance using historical trends, seasonality, and automatic model selection. See where your metrics are headed — not just where they've been.
How it works
The forecasting engine analyzes your historical data to detect:
- Trend direction (growing, declining, stable)
- Seasonality (weekly or annual patterns)
- Volatility (how stable the metric is)
- Mean reversion (whether the metric tends to return to a baseline)
Based on these characteristics, it automatically selects the best model for your specific data.
Models used
| Model | Best for |
|---|---|
| Mean Reversion | Stable, cyclical apps with no strong trend |
| Damped Trend | Apps showing growth or decline that's expected to slow |
| Seasonal Naive | Very seasonal apps (uses last year's values as baseline) |
| Exponential Smoothing | High-volatility apps (weighs recent data more heavily) |
The system explains which model was selected and why.
Metrics available for forecasting
| Metric | Display Name |
|---|---|
proceeds | Net Revenue |
total_revenue | Gross Revenue |
total_downloads | Total Downloads |
active_subs | Active Subscriptions |
new_trials | New Trials |
Note: Ad spend metrics are intentionally excluded — ad campaign decisions are human choices, not organic trends that can be modeled.
Forecast output
Each forecast includes:
- Historical data — your actual past values
- Forecasted values — projected future values
- Confidence interval — upper and lower bounds (95% confidence by default)
- Trend direction — up / down / stable
- Trend strength — 0–100 score
- Model used — which algorithm was selected and why
Default: 24 weeks forward, using 24 weeks of history. You can extend up to 3 years forward with 3 years of history.
How to use it
- Go to Forecasting in the sidebar.
- Select an app (asset).
- Choose a metric to forecast.
- Adjust the forecast window if needed.
- Review the chart and the model selection explanation.
Interpreting the results
The confidence interval shows the range Fload expects your metric to land in. A wide band means high uncertainty (volatile data); a narrow band means high confidence (stable, predictable data).
The trend strength score indicates how much directional momentum the data has:
- 0–20: Effectively flat
- 20–50: Mild trend
- 50–80: Strong trend
- 80–100: Steep sustained trend
Minimum data requirement
Forecasting requires at least 90 days of historical data. If your app is newer or your connector was recently connected, forecasts may not be available yet.
Asking the AI about forecasts
The AI chat can discuss forecasts: "What does my revenue forecast look like for Q4?" or "Is my subscriber growth trending up?" The AI uses the same forecasting engine and can provide narrative interpretation alongside the numbers.