Corinna Covini, Copenhagen Fintech: What has Predicti been working on?

Luke Tricker, Head of Marketing: We have built a housing prediction model that looks at who is most likely to buy a new home within the next 12 months in Denmark. If you look at the local housing market, there are approximately 1.4 million owned houses orapartments.

With our prediction model, if you were to contact the top 20%, around 280,000 out of that 1.4 million, we would be able to identify nearly 60% of the total number of buyers for the next 12 months.

Corinna: Who is this product relevant for?

Luke: It is relevant for anything connected to the home buying process: estate agents, banks looking at mortgage products, home insurance providers, moving insurance providers, and customer relationship management teams.

We want to enable insurers and banks to be proactive in customer engagement rather than reactive, and to reach out to customers sooner in the process.

The model ranks addresses by likelihood, helping financial institutions understand which households to contact earlier in the homebuying journey.

Corinna: Which impact does this product have on your customers?

Luke: With a recent customer, their outreach became at least 9 times more efficient in identifying customers with actual intent to buy a house, when using the model, compared to traditional outreach.

Corinna: What is the secret sauce of this prediction model?

Amalie Palmund, Data Scientist: I would say the way the data is set up. The model has been built from Danish registry and publicly available data sources, including historical data on people who have actually moved from 2020 onwards.

We now have software that combines these different data sources into logical timelines.

We use the address as a proxy. We are not saying that a specific named person will buy ahome. We are ranking addresses and households by likelihood, and can say whether one address is more likely to buy than another address ranked below it.

‍

Corinna: What has been one of the hardest parts of building this?

Amalie: Making sure the output was correct. The initial building process was relatively fast, and the first results we got were surprisingly good. But we still spent a lot of time testing and making sure that we had no feature leakage or data leakage that would alter the predictions.

The way we tested it was by training the model on historic data up to 2024. That gave us the full year of 2025 to compare the model against publicly available data and ask: did the predicted households actually buy something in the next 12 months?

‍

Corinna: Where will Predicti go from here?

Luke: This housing prediction model is the first of our new ML models that have been built and trained on top of our collected data platform. We have many more in the pipeline, such as being able to predict which life stage someone is about to enter, or which kind of customer segment they are moving into.

If an insurer or a bank came on board with us tomorrow, we would give them access to the platform where we collect all the data sources together, and then their data science teams could build their own models based on their customer data. You could build advanced churn models, product recommendations and much more. There are a lot of data scientists out there who would have many ideas.

Amalie: We also meet smaller or medium-sized customers that do not have a large data science team, or may not have one at all. In those cases, we can build models for them in-house.

‍

Corinna: Which sector problem can Predicti help solve with more customized predictive models?

Luke: Insurers and banks often have legacy systems that are fragmented and hard to extract data from.

For these teams, it would take a long time to build something like what Amalie has built for Predicti, because they would first have to collect the datasets, connect the historical information and manage all the different moving parts.

Predicti already has a validated setup. We could take their data, put it into our system, and it would be almost ready to plug and play.

Corinna: How has being Nordic-based impacted this development journey?

Luke: Being Nordic-based has worked to our advantage. Across the region, digital adoption is high compared with much of Europe, particularly in insurance and banking. The Nordic region is one of the most digitally mature regions in Europe.

If you think about life in Denmark, everything is connected to your CPR number. Everything is online, you can log into services easily, and there is a lot of digital self-service in everyday life. People expect that same level of personalization and ease from their insurer and their bank.

What we do is enable the personalization people already expect in other areas of life, but within their insurance and banking interactions.

Platforms like Copenhagen Fintech's Beyond Nordic Scaleup Program also support knowledge sharing among scaling peers. Getting to meet other people in the industry, see what they are doing, and connect at events such as Nordic Fintech Week is valuable. The collaborative aspect of the ecosystem is a strong asset.

Corinna: Where do you see the sector going?

Luke: I believe hyper-personalization products like the ones Predicti is building are the direction of travel.

If you think about social media, IKEA or other digital services, they treat you much more as an individual than many financial services do today. I think more localized messaging and more personalized offerings are where the sector is heading.

‍