Get started with ML faster with our unique AI FlightCheck service

Martin Stewart - Jul 29, 2024

Machine Learning (ML) makes a broad set of AI-driven scenarios possible—beyond the generic capabilities of Generative AI. By applying proprietary ML models, (pre-trained in our Hornbill AI Lab) to your own data, we’re opening up new opportunities to apply AI to more service management scenarios.

Unlike GenAI (which relies on publicly available data to train a general-purpose model), the targeted ML models that we’re adding to Hornbill Service Manager use your service management data to deliver specific insights and actions that are unique to your organization.

Data quality is the key to successful machine learning

The success of machine learning relies on the quality of data that is fed into it. The principle of "Garbage-In-Garbage-Out" (where bad data going in means bad data coming out) applies as much to AI as it does to any other IT system. But many organizations struggle to assess and prepare their data. It’s one of the biggest barriers to machine learning readiness and adoption.

At Hornbill, we’re always looking at how we can remove the barriers that stand in the way of technology adoption. It’s our job to make it easy for our customers to use the latest technology. That’s why we’ve created HAi FlightCheck—a unique service that takes the pain out of assessing and preparing your data in readiness for the ML-driven ITSM features in our AI Roadmap (see our Hornbill AI Lab).

What is HAi Flight Check?

Our AI Flight Check service is a solution to the challenges or ML data readiness—designed to accelerate and smooth-out the path to adoption—by taking the complexity and hard work out of assessing and cleaning your service management data.

The FlightCheck service is enabled by our consultants and a set of purpose-built tools. These tools automate the process of analysing and assessing your data—telling you precisely where there are data quality anomalies and concerns that could compromise the output of Hornbill's ML models.

That means you don’t need to manually trawl through your data to find and eliminate issues—which could take weeks or months. Our consultants will run the tools, analyse the data to pinpoint specific problems, and work with you to quickly resolve them. During this process, your data remains secure and won’t leave your Hornbill instance.

HAi FlightCheck AI readiness methodology

With Hornbill FlightCheck, you can get started with advanced AITSM features faster—saving weeks of manual data analysis.

How does it work?

FlightCheck uses a set of statistical analysis and visualisation techniques (such as t-SNE) to automatically pinpoint data cleanliness issues. It’s about finding the anomalies to shine a light on where data needs work before it’s a viable source for an ML model.

For example, FlightCheck will analyse and visualise your service desk data to find incorrectly categorised tickets. It does this by looking at the structured and unstructured ticket data to cluster tickets and surface anomalies that indicate categorisation issues.

Hornbill FlightCheck t-SNE analysis

These statistical methods are not commonly used in the ITSM world, so FlightCheck enables our customers to bypass the complexity and the steep learning curve to get what they really need—a checklist of the data quality issues to be resolved so that they can quickly become “AI ready”.