Skip to content
fernet.consultores

Artificial Intelligence

AI you can audit.

We apply artificial intelligence where it improves a decision you already make today, with controlled data, measurable results and a record of what each system does that you can explain to management, auditors and regulators.

A fixed threshold doesn't know what time it is

The same metric over two days, watched two different ways. Move the fixed threshold and the model's sensitivity, and compare how many alerts each one fires and how many of the two real anomalies it catches.

Synthetic example series. The orange dots above are fixed-threshold alerts; the pink ones below are from the adaptive model.

Fires whenever the metric exceeds this value, at any time.
How many standard deviations the value strays from what's expected at that hour.

Fixed threshold

Alerts
0
False alarms
0
Real anomalies detected
0 of 2

Adaptive

Alerts
0
False alarms
0
Real anomalies detected
0 of 2

In Splunk we solve this with adaptive thresholds in ITSI or with Machine Learning Toolkit models trained on your own history.

How we work.

Five phases, always in the same order. Select each one to see what happens in it.

We identify the use case, the data available, the risks and how success will be measured.

We design the solution: models, data, integrations, security controls and traceability.

We build a first, tightly scoped version on a real use case, with evaluation from day one.

We measure quality, cost and risk with real data before extending its use.

We tune the system based on real usage and monitor the system like any other production service.

Start with a conversation.

Tell us about your situation and we will tell you frankly which service fits and where to begin.

Talk to us about Artificial Intelligence