Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.rolearn.dev/llms.txt

Use this file to discover all available pages before exploring further.

CCU Forecasting uses advanced time-series machine learning to predict future player counts for any tracked game.

How It Works

RoLearn collects historical player count data for your tracked games, processes it through our forecasting pipeline, and generates predictions with confidence intervals. Models are retrained regularly to stay accurate as game dynamics change.

Features

  • Point forecasts: Expected CCU for each future day
  • Confidence intervals: Upper and lower bounds showing prediction uncertainty
  • Trend decomposition: See seasonal patterns (weekday vs. weekend, holidays)
  • Multiple horizons: Short-term (7d) and long-term (30d) projections

Using Forecasts Effectively

Forecasts are most useful for answering directional questions:
  • “Is this trend still growing or has it peaked?” — Check whether the forecast line is trending up or down
  • “Should I build something similar?” — If a game’s forecast shows sustained growth, the window is still open
  • “When should I expect a dip?” — Weekly and seasonal patterns show natural low points
Combine forecasts with Game Benchmarking to understand if predicted growth is above or below genre norms.

API Endpoint

GET /api/forecast/{place_id}
See API Reference → Forecast for full details.

Plan Limits

PlanForecast Access
Explorer
BuilderBasic (7-day)
StudioAdvanced (30-day + confidence intervals)

Frequently Asked Questions

RoLearn generates CCU forecasts based on historical patterns and seasonal trends. While no prediction is perfect, forecasts give you a strong directional signal — whether a game is growing, stable, or declining.
Builder plans get 7-day forecasts. Studio plans unlock 30-day forecasts with full confidence intervals. Longer history on a tracked game improves forecast accuracy.
Games with 30+ days of tracking history produce the most reliable forecasts. Major game updates can temporarily reduce accuracy until enough post-update data accumulates. The confidence interval width tells you how certain the model is.