RG Score Reference | Virtual Stadium | Sportradar Developer Documentation

The RG Score is a composite risk score between 0 and 100 assigned to each user for each of four time windows. It gives operators a single, easy-to-read number that summarizes multiple behavioral signals, making it straightforward to sort and prioritize users in the queue.

This page explains what the score measures, how it is calculated, and what the different score ranges mean in practice.

#Score Formula

For each time window (7d, 30d, 180d, 365d), the RG Score is the sum of five components:

$$\text{RG Score} = E + R + P + C + S$$

Component	Maximum points	What it measures
E — Evidence	40	How many messages were flagged and how confidently
R — Ratio	20	What proportion of the user's messages were flagged
P — Persistence	20	How many separate days had at least one flagged message
C — Change	15	Whether flagged activity has increased compared to the previous window
S — Same-day cluster bonus	5	Whether a large number of flagged messages appeared on a single day

The maximum possible score is 100.

Why five components?

A user who sends a very high volume of messages will naturally accumulate more flagged messages than a low-volume user, even if their ratio of flagged to total messages is similar. The five-component model corrects for this by treating volume, ratio, persistence, trend, and acute daily spikes as separate signals. An individual user's score reflects the full picture of their behavior rather than just raw flagged count.

#Shared Definitions

Flagged message — A message with a model probability score of 0.60 or above. The probability score represents the model's confidence that the message belongs to the at-risk class.

Average flagged probability — The mean probability score across all flagged messages in the window. Used only within the Evidence component as a small confidence bonus.

Flagged ratio — Flagged messages divided by total messages in the window.

Distinct flagged days — The number of separate calendar days in the window that contain at least one flagged message.

Change — The difference in flagged message count between the current window and the previous equivalent window (e.g., current 7d versus the 7d before that). If no prior window data exists for a user, Change points are set to 0.

Same-day cluster — The maximum number of flagged messages sent on any single day within the window.

#7-Day Score

The 7-day score is the primary operational score. It drives triage queue sorting and alert triggering. Use it for daily prioritization and urgent outreach decisions.

#Evidence (0–40)

Flagged count points (0–30)

Flagged messages (7d)	Points
0	0
1	5
2	10
3	15
4–5	20
6–7	25
8 or more	30

Confidence bonus (0–10)

Average flagged probability	Bonus
Below 0.65	0
0.65 to below 0.75	4
0.75 to below 0.85	7
0.85 or above	10

#Ratio (0–20)

Minimum of 3 flagged messages required; otherwise Ratio points are 0.

Flagged ratio (7d)	Points
Below 5%	0
5% to below 10%	6
10% to below 20%	13
20% or above	20

#Persistence (0–20)

Distinct flagged days	Points
0	0
1 day, daily max below 3	0
1 day, daily max 3 or above	3
2 days	6
3 days	12
4 days	16
5 or more days	20

#Change (0–15)

Increase in flagged count vs previous 7d	Points
No increase or decrease	0
Increase of 1–2	5
Increase of 3–4	10
Increase of 5 or more	15

#Same-Day Cluster Bonus (0–5)

Max flagged on a single day	Points
0–2	0
3–4	3
5 or more	5

#30-Day Score

The 30-day score is the secondary operational score. Use it to identify users with sustained patterns over a longer period and to prioritize follow-up outreach when the 7-day score is borderline.

#Evidence (0–40)

Flagged count points (0–30)

Flagged messages (30d)	Points
0	0
1–2	4
3–5	10
6–8	17
9–11	22
12–15	27
16 or more	30

Confidence bonus is the same table as 7d.

#Ratio (0–20)

Minimum of 5 flagged messages required; otherwise Ratio points are 0.

Flagged ratio (30d)	Points
Below 3%	0
3% to below 8%	6
8% to below 15%	13
15% or above	20

#Persistence (0–20)

Distinct flagged days (30d)	Points
1 day	0
2–3 days	6
4–6 days	12
7–10 days	16
11 or more days	20

#Change (0–15)

Increase in flagged count vs previous 30d	Points
No increase or decrease	0
Increase of 1–3	5
Increase of 4–7	10
Increase of 8 or more	15

#Same-Day Cluster Bonus (0–5)

Same table as 7d.

#180-Day Score

The 180-day score provides historical context. Use it during a user review to understand whether a current spike is part of a longer pattern or an isolated event. It is not used for alerting.

#Evidence (0–40)

Flagged count points (0–30)

Flagged messages (180d)	Points
0	0
1–3	4
4–7	8
8–14	14
15–24	19
25–39	25
40 or more	30

Minimum of 10 flagged messages required for Ratio points; otherwise Ratio points are 0.

#Ratio (0–20)

Flagged ratio (180d)	Points
Below 2%	0
2% to below 5%	6
5% to below 10%	13
10% or above	20

#Persistence (0–20)

Distinct flagged days (180d)	Points
1–2 days	0
3–5 days	6
6–12 days	12
13–24 days	16
25 or more days	20

#Change (0–15)

Increase vs previous 180d	Points
No increase or decrease	0
Increase of 1–5	5
Increase of 6–14	10
Increase of 15 or more	15

#Same-Day Cluster Bonus (0–5)

Max flagged on a single day	Points
0–3	0
4–5	3
6 or more	5

#365-Day Score

The 365-day score provides long-term tracking and historical risk context. Use it for compliance reporting and to understand a user's history across a full year. It is not used for alerting.

#Evidence (0–40)

Flagged count points (0–30)

Flagged messages (365d)	Points
0	0
1–5	4
6–12	8
13–24	14
25–49	19
50–79	25
80 or more	30

Minimum of 15 flagged messages required for Ratio points; otherwise Ratio points are 0.

#Ratio (0–20)

Flagged ratio (365d)	Points
Below 1%	0
1% to below 3%	6
3% to below 7%	13
7% or above	20

#Persistence (0–20)

Distinct flagged days (365d)	Points
1–3 days	0
4–8 days	6
9–20 days	12
21–40 days	16
41 or more days	20

#Change (0–15)

Increase vs previous 365d	Points
No increase or decrease	0
Increase of 1–8	5
Increase of 9–24	10
Increase of 25 or more	15

#Same-Day Cluster Bonus (0–5)

Same table as 180d.

#Score Bands

The numerical score maps to a descriptive label. Labels differ between the operational windows (7d and 30d) and the historical windows (180d and 365d).

#7-Day and 30-Day (Operational)

Score	Label
0	No observed concern
1–24	Low priority
25–49	Review recommended
50–74	Outreach candidate
75–100	High priority

#180-Day and 365-Day (Historical Context)

Score	Label
0	No observed history
1–24	Occasional incident
25–49	Moderate history
50–74	Elevated incident rate
75–100	Significant history

note

The 180-day and 365-day labels are provided as background context for moderator reviews, not as urgent action triggers. Decisions to act on a user should primarily be based on the 7-day and 30-day scores.

#Score Update Intervals

Window	Update frequency
Flagged message history	Near real-time
7-day RG Score	Every 15 minutes
30-day RG Score	Every 60 minutes
180-day RG Score	Once daily
365-day RG Score	Once daily

All windows use a rolling trailing calendar-day window in the operator's local timezone. For example, the 7-day window covers today plus the previous 6 calendar days.

#Alerts and Scores Are Independent

It is expected and by design that a user can trigger an alert while still having a low or moderate RG Score. Alerts are intentionally more sensitive than the score — they react to a single strong signal within the 7-day window — whereas the score reflects a balanced combination of all five components across the full window. Treat an alert as "look at this user now" and the score as an overall pattern of behavior.