ARIA Platform / Finance & Planning
Finance & Planning Suite

Sales Forecasting Dashboard

Statistical time-series forecasting that runs entirely in your browser. STL decomposition separates trend from seasonality. Holt-Winters exponential smoothing generates 12-month forward projections with confidence intervals. No backend, no data leaving your machine — powered by Python WASM (Pyodide) running locally.

aria.cloud/finance/forecasting
A Sales Forecasting — Total Revenue Holt-Winters Run model 12-month forecast € 86.4M CI: € 78.2M – € 94.6M Trend direction +4.2% Annualized growth Forecast accuracy 94.2% MAPE: 5.8% Seasonality index 1.24 Peak: Q4 (124%) Engine Python WASM (Pyodide) NumPy · Statsmodels · SciPy In-browser Revenue time series — 36 months historical + 12 months forecast 0 €3M €6M €9M 2024 2025 2026 2027 (forecast) Today Historical Forecast 95% CI Trend
Statistical forecasting, no data science team required
Upload your historical data, select a model, and get a forecast with confidence intervals — all running locally in your browser via Python WASM. No server, no latency, no data leaving your machine.
Decomposition

STL decomposition: trend, seasonality, residual

Before forecasting, understand your data. STL (Seasonal and Trend decomposition using Loess) separates your time series into three components: the underlying trend, the seasonal pattern, and the unexplained residual. This reveals whether your growth is real or just seasonal, and whether your data has anomalies worth investigating.

  • Automated period detection (monthly, weekly, daily)
  • Trend extraction showing real growth vs seasonal effects
  • Seasonal pattern visualization across years
  • Residual analysis for anomaly detection
STL decomposition — 36 months Trend +4.2% annualized Seasonal 12-month cycle detected Residual σ = € 0.18M Anomaly: Dec 2025 Trend explains 68% · Seasonality 26% · Residual 6% of total variance
Holt-Winters

Exponential smoothing with confidence intervals

The Holt-Winters method captures level, trend, and seasonality in three smoothing equations. AERA auto-optimizes the alpha, beta, and gamma parameters to minimize forecast error. The result: a point forecast with 80% and 95% confidence intervals that widen as the horizon extends — showing uncertainty honestly.

  • Triple exponential smoothing (additive or multiplicative)
  • Auto-optimized α, β, γ parameters (grid search)
  • 80% and 95% confidence bands
  • 12-month rolling forecast updated monthly
Holt-Winters forecast — 12 months ahead Model parameters (auto-optimized) α = 0.42 (level) β = 0.08 (trend) γ = 0.35 (season) Month Forecast Lower 95% Upper 95% Seasonal CI width Apr '26 € 6.8M € 6.2M € 7.4M 0.96 ± 8.8% Jul '26 € 7.4M € 6.4M € 8.4M 1.08 ± 13.5% Oct '26 € 8.2M € 6.8M € 9.6M 1.24 ± 17.1% Mar '27 € 7.0M € 5.4M € 8.6M 1.02 ± 22.9% Backtest accuracy (last 12 months) MAPE: 5.8% RMSE: € 0.42M Coverage: 96% in CI vs Naive: +34% better
Seasonality

Seasonal pattern analysis with monthly indices

Understand when your peaks and valleys occur. The seasonal index for each month shows how much above or below average that month typically performs. Q4 spike for manufacturing companies? Summer dip for B2B services? AERA quantifies it precisely so your budget reflects reality, not hope.

  • Monthly seasonal index (1.0 = average, 1.24 = 24% above)
  • Year-over-year seasonal pattern comparison
  • Seasonal adjustment for trend-only analysis
  • Feeds directly into sales budget for monthly distribution
Seasonal index — monthly pattern 1.0 avg Jan0.82 Feb0.78 Mar1.05 Apr1.08 May1.12 Jun1.06 Jul0.84 Aug0.72 Sep1.04 Oct1.16 Nov1.20 Dec1.24 Peak: Dec (124%) — Q4 accounts for 30% of annual revenue · Trough: Aug (72%) — summer shutdown effect
See it in action
A walkthrough of the Forecasting Dashboard — from data upload through decomposition to forecast generation and accuracy tracking.
Video coming soon
94.2%
Forecast accuracy
Pyodide
Python in-browser
STL
Decomposition
12mo
Forward horizon
Ready to forecast with confidence?

No forms, no sales funnel. Just a conversation about what ARIA can do for your sales forecasting.