Platform/Causal Incident Intelligence
Causal Incident Intelligence

From an alarm flood to one incident with a named origin

A single device fault produces hundreds of correlated alarms buried in background noise. Raincurve decides which alarms belong together — and which one started it.

0.85Pairwise F1 grouping alarms into incidents, vs 0.67 for a topology-window rule engineHawkes study, simulated
75%Incidents where the root-cause device was identified, vs 42% for tuned rulesHawkes study, simulated
1.8Tickets per incident, vs 2.9 for rules and 9.0 for time-gap groupingHawkes study, simulated
0.04 sTo group 3,348 alarms from a six-hour window on a laptopHawkes study
How it works

Alarms either happen on their own, or something caused them.

Raincurve models alarms as a Hawkes process — the same statistics used for earthquake aftershocks. Every alarm is either background (a genuine origin or routine noise) or triggered by an earlier alarm, with influence that decays over time.

Excitation is constrained to devices that are physically connected, and two decay timescales capture both hop-by-hop propagation (seconds) and repeated polling (minutes). The model is fit with expectation-maximization and needs no labels.

The result is a most-likely parent chain for every alarm. Follow it back and you reach the origin.

Auditable by design

The model learns the cascade an engineer would draw.

Without any labels, the learned excitation matrix recovers relationships like routing adjacency loss driving host-unreachable alarms one hop away. Operators can read it, question it and override it.

Rule engines fail under noise because they pull in every nearby alarm. The Hawkes model asks whether an alarm is better explained by a cascade or by its normal background rate — so routine events stay out of the incident.

Learned cascadestrength
1.89
Routing adjacency down → host unreachable
1 hop
1.33
Routing adjacency down → application timeout
1 hop
0.44
Optical degradation → optical degradation
same device
0.40
Optical degradation → link down
same device
0.39
Host unreachable → application timeout
same device

What operators get

One ticket per incident

Related symptoms across layers arrive as one incident, not a queue of duplicates across teams.

A ranked origin

The most likely root-cause device and signal, with the parent chain that led there.

Robust to messy telemetry

Tested with 15–40% alarm loss, clock skew up to 60 seconds and overlapping incidents.

Noise that stays noise

High-base-rate events like periodic CPU spikes are explained away instead of grouped in.

Cross-layer narrative

Network, compute, cloud and application symptoms combined into a single timeline.

Real-time

Grouping is fast enough to run continuously on commodity hardware.

Make infrastructure intelligence operational.

Start with a conversation about your environment.