With a massive amount of data, humans must identify changes in performance and take action on that insight.

Moreover, it’s hard to interpret the meaning of a specific shift in a metric that could be innocuous or a life-changing opportunity for growth.

Veos Digital Anomaly Detection Service (VDAD) suits those companies that strive to:

  • discern between insignificant events and events that are truly unusual, and therefore calling for action
  • let people focus on strategy, reducing time-consuming activities
  • have a unique interpretation of data shared between teams

Anomaly definition

Anomalies can be classified into two categories: 

  • Expected Anomalies are generally well understood and easily connected to specific events
  • Unknown Anomalies are not understood, and humans cannot predict them

Veos Digital Anomaly Detection Service addresses Unknown Anomalies.


Our anomaly detection solution identifies data points deviating significantly from expected behavior. Only anomalies are shown to users–reducing their cognitive load and allowing them to tell apart signals from noise.

VDAD can be applied to data with high quality and one of the measurements within the data contains sufficient information to reveal the anomaly, such that a human operator, given sufficient time and skill, would be able to unearth it.

VDAD can be also applied to dataset whit a new key variable to the mix – time.  In many applications, they are vital for representing the normal behavior of a system.

Scientific basis

Veos Digital Anomaly Detection Service is based on Time Series Analysis.

VDAD leverages unsupervised learning techniques, so the system intelligently assesses the datapoint likely to be historical anomalies and returns that to the user, alongside determining this for future datapoint.

Use cases

Anomaly detection can also be used for marble issues identification.

Here’s an example of few sample of marble photos analyzed to find the imperfection.

Marble anomaly detection

On the other side, we can use AI to collect anomalies in Agritech industries. In this example, the algorithm is highlighting the leaf rice with a potential HISPA (Dicladispa armigera).

Rice HISPA anomaly detection


Our system is RESTful APIs based. It’s a standard adopted by many Software producers to provide applications to Third Parties.

Simple integration

Zero maintenance

Pay per use