Six Months of Data Reveal a Clear Seasonal Cycle
The data now spans November 2025 through April 2026 — revealing a clear seasonal cycle. January/February benefits renewal creates a production peak that the R8 rolling average anchors to. By March/April, production returns to November/December baseline levels, making the R8 prediction unreachable.
Weekly Network Production Trajectory
Total weekly production across all practices with R8 prediction overlay
Peak Month (Jan)
$7.06M
$7,058,729/wk
Current (Apr)
$6.34M
$6,338,364/wk
R8 Prediction
$7.54M
$7,539,503/wk
Peak-to-Current Drop
-10.2%
Jan to Apr decline
Dec ≈ Apr
Cyclical
$6.33M ≈ $6.34M
Monthly Summary by Day of Week
| Month | Mon | Tue | Wed | Thu | Fri | Weekly Total | vs R8 | vs January |
|---|
Is the R8 the Wrong Tool?
A seasonal model (comparing to same-month-last-year) or a weighted model (heavier on recent months) would be more accurate than a flat rolling average that treats January the same as April. The R8 anchors to the Jan/Feb peak and will always overpredict during the spring and fall troughs.
Production Trajectory with Projections
Actual weekly production (solid) extended into May/June (dashed) with R8 overlay
R8 Predicts
$32.4M/mo
Anchored to Jan/Feb peak. Treats all 8 weeks equally — including the two best months of the year.
Trend Predicts (May)
$28.8M/mo
Based on 6-month linear regression of each DOW. More conservative but doesn't model seasonality either.
Seasonal Insight
Apr ≈ Dec
If April tracks December, then May should recover toward January levels as summer demand rises — unless the declining practice cluster drags it down.
DOW Linear Regression Detail
| Day | Slope ($/mo) | May Predicted | Jun Predicted | R8 | May vs R8 |
|---|
R8 Rolling Average Formula
The R8 prediction is a simple rolling average of the last 8 weeks of production for each day of the week, calculated per-practice.
- Window: 8 weeks (rolling)
- Granularity: Per-practice, per-DOW
- Network R8: Sum of all practice-level R8 values per DOW
- Weekly R8: $7,539,503 = Mon ($1,687,831) + Tue ($1,815,123) + Wed ($1,672,127) + Thu ($1,624,296) + Fri ($740,126)
$300 Threshold
Any practice reporting less than $300 in daily production is excluded from that day's calculation. The $300 threshold represents approximately one doctor-day of minimum production — below that, the practice likely had no provider and the zero would distort the average.
Data Sources
- 83 practices: Direct VELOX reporting with daily production actuals
- 7 practices: Estimated from monthly aggregates (no daily VELOX feed)
- 90 total: Represent the SGA network for pacing analysis
- Timeframe: November 2025 through April 2026 (6 months, ~130 business days)
Prediction Model: Linear Regression
The "Trend Predicts" values use ordinary least squares (OLS) linear regression on each DOW's 6-month series. Each month is assigned an index (Nov=1, Dec=2, ... Apr=6) and the regression fits production = slope * month_index + intercept.
- May prediction: month_index = 7
- June prediction: month_index = 8
- Limitation: Linear regression assumes a constant trend. It does not model seasonal cycles. The December anomaly (Monday = $754 due to holidays) skews Monday's slope upward.
The Seasonal Pattern
Six months of data reveal a clear seasonal U-curve:
- November: $6.79M/wk — baseline production
- December: $6.33M/wk — holiday trough (fewer working days, patient cancellations)
- January: $7.06M/wk — benefits renewal peak (new insurance year, pent-up demand)
- February: $7.04M/wk — sustained renewal effect
- March: $6.94M/wk — beginning to fade
- April: $6.34M/wk — returns to December baseline levels
December and April are nearly identical ($6.33M vs $6.34M), confirming this is a seasonal cycle rather than a structural decline. The R8 will always overpredict during trough months because it includes January/February in its 8-week window.
Power BI Direct Integration
The dataset ID b57375c9-d64b-4643-be71-378a520d8f93 was extracted from the Excel connection string. A direct API integration is feasible via:
POST https://api.powerbi.com/v1.0/myorg/datasets/b57375c9-d64b-4643-be71-378a520d8f93/executeQueries- This would eliminate the Excel middleman and enable automated daily refresh
- DAX queries can be sent directly — the same measures used in Power BI reports
- Requirements: Azure AD service principal with Power BI API permissions (
Dataset.Read.All)
- Benefit: Dashboard could pull live data instead of requiring manual Excel exports
- Status: Proof-of-concept validated via the Power BI bridge at VPS:3050. Full automation requires Azure AD app registration and service principal setup.