An inhouse-developed data stack is automating, personalising, segmenting and curating for Freiburg publisher Badische Zeitung.

In an INMA case study digital content chief Markus Hofmann tells how Badische Zeitung took “a handful of data sources and some smart algorithms, built a few applications and fed them with lots of data”.

The story of the multifunctional tool the newspaper publisher developed over a period of years sounds simple, but as Data Machine it handles its most important resource.

“We deploy this machine to systematically: automate production processes; personalise digital products; segment our audience using marketing automation; build new habits, and curate content,” he says.

Data is collected via external services such as Piano, Smartocto and Chartbeat, but Hofmann says its “real power and magic” comes from interacting with BZ’s own applications and algorithms.

Here are some examples.

-On social media, some content is published automatically. The main Twitter  is fuelled by engagement data powered by Piano in real time, and this acts as a trigger. As soon as an article reaches a threshold, an algorithm of Data Machine fires a tweet, generating keywords, and a paid content label if necessary.

Hofmann says automation has had a big impact on Twitter reach, increasing referral Twitter traffic by more than 100 per cent in a year.

On personalisation, he cites BD’s Die Woche (The Week) a list inspired by Spotify’s Discover Weekly. Based on individual reading habits, it recommends stories from the past week which a reader hasn’t yet read.

Algorithms show only the most engaging stories of the week, an engagement score having been added to an article by content analytics service Smartocto. Piano provides the personalisation.

Badische Zeitung also deploys Piano’s marketing automation tools, in one example recommending hiking tours a a means to acquire new digital subscribers. In website article views, Piano’s personalised content recommendations were integrated, showing even more hiking tours stored in the archive in an exclusive personalised module.

“We called it The Hiking Lasso,” he says. “Even our paywall was personalised for this audience segment with an atmospheric photo of the Black Forest.”

The campaign delivered almost 150 new digital subscribers.

Badische Zeitung launched a new newsletter service, BZ am Abend (BZ in the evening) in March 2020, some days before the first COVID-19 lockdown in Germany. Published at 7 pm six days a week, it goes to more than 100,000 readers.

Hofmann says the “magic” is that the newsletter runs almost completely automatically: “Exactly one hour before distribution, an algorithm selects the most popular content published in the past 24 hours, considering engagement data provided by Piano.

“We are able to assign most of the articles to local communities, reaching newsletter subscribers who share their postcode when signing in.

“By this means, our newsletter has a very local flavour.”

He says the Data Machine algorithm creates more than 200 variants of local newsletter editions automatically, scoring an average open rate of 30 per cent. “It’s one of the most important services of BZ to habitualise readers and build new rituals,” he says.

Most articles from the printed newspaper are also distributed digitally, with the newsroom optimises only a small percentage of these articles for digital channels by adding an extra headline or a special photograph. “However, our editors know that if they optimise newspaper content for the web, they can boost reach and engagement.”

The question is therefore, which of the more than 300 articles daily should get channel-specific optimisation? Data Machine supports the newsroom by making the decision. “A smart bot analyses engagement data of the printed content after it’s published online and gives recommendations via email as to which articles should be optimised.

“By this means, Data Machine reduces the cognitive load of our editors and saves them time.”

Hofmann says the examples show that a strict focus on data can leverage value and efficiency. “Even before the COVID-19 peak, Badische Zeitung demonstrated a strong digital presence with almost 34,000 digital subscribers and an exponential growth rate,” he says. “For the first time in ten years, we saw a positive growth rate of our total subscriber base (print + digital).

“Above all, this is the merit of the newsroom and our editors. Data Machine helped them to do their jobs.”

• This case study originally appeared in the INMA report, The Guide to Smart Data Strategy in Media