Identify Water Leaks
To evaluate how well AI can classify cases as water leak–related, creating a new datapoint that can be used in maintenance planning and analysis.
Tid | TBD |
|---|---|
Plats | Digitally |
What we want to solve
By analyzing the text in case descriptions, we want to automatically classify whether a case is related to a water leak or not.
This creates a binary datapoint for every case:
Water leak: Yes / No
This datapoint can then be used in dashboards, analyses, and maintenance planning to identify where and how often water leaks occur in the property portfolio.
Example case description:
”Water has started to run down into the hallway from the ceiling. We suspect that a pipe in the wall has burst.”
Generated datapoint:
Water leak: Yes
What value does it create?
With better insights into water leaks, property management can make more accurate decisions regarding planned maintenance, especially for piping, waterproofing, or plumbing systems.
Example:
”We were able to prioritize the right buildings in this year’s maintenance budget, since we identified a pattern of water leaks in certain properties.”
What happens if we don’t do this?
Risk of incorrect priorities in maintenance budgets.
Higher costs due to emergency repairs.
A worse living environment for tenants.
For whom?
This test is aimed at those who:
Are responsible for maintenance planning or technical property management.
Make decisions about investments in plumbing systems, waterproofing, or piping.
Work with analysis and follow-up of property operations and costs.
The test group’s mission
Over six weeks, we will jointly evaluate the solution in three structured workshops of 1.5 hours each. The goal is to understand how the classification works and assess the value it can create in decision-making.
Session 1 – Kick-off
We will review a dashboard with categorized cases and discuss how it is intended to be used. You will also receive a sample of 100 cases with their respective classifications.
👉 Between sessions: Review the sample, assess whether you agree with the classification, and evaluate if the categories themselves are relevant.
Session 2 – Decision making
We will discuss together: What decisions would you like to make – or believe you could make – based on the data? How could it be used to guide maintenance planning, investments, or proactive risk management?
Session 3 – Evaluation
We will evaluate the solution by asking: Does the classification create actual value? Has it already led to decisions, or do you see that it could in the future? In which situations is the information most useful – during budgeting, maintenance strategy, or daily operations?
Why participate?
As a participant in the test group you will:
Have a unique opportunity to influence the continued development of the solution.
Gain early insights into where water leaks occur and how often.
Take part in discussions about how data can be turned into decisions that reduce costs and improve the tenant experience.
Directly impact which features and priorities are developed next.
Participation requirements
The test group has a limited number of places. To participate, you need to:
Submit your role and a short motivation explaining why this information is important to you.
Describe which decision(s) you hope to make based on the material.
Commit to attending all three sessions and set aside time between meetings to review the sample cases.
