Anyone can publish on Medium per our Policies, but we don’t fact-check every story. For more info about the coronavirus, see cdc.gov.

New model suggests investors use FT to make sense of pandemic market chaos

Jono Hutchison
Jun 16 · 3 min read

A new data model built to identify why people are accessing the Financial Times has highlighted the impact of recent market turmoil on how subscribers make use of the FT.

The ‘user modes’ model is a framework for identifying the purpose of a site visit. A user can exhibit a range of ‘modes’ across their different visits; for example, they might be researching at work but browsing headlines and news stories to stay up-to-date at home.

The model “gives us more of a clue as to why a user is accessing various parts of the site. Two people could be viewing the same article but have different reasons for doing so,” explains Data Scientist Cloudy Carnegie, who worked with Adam Gajtkowski, Peter Harris and other colleagues on the project.

The months of March and April were tumultuous for global equity and commodity markets, as the coronavirus pandemic created vast uncertainties and heaped pressure on already-depressed oil prices. During this period there have been several ‘firsts’, including US oil prices turning negative for the first time in history.

This chart shows the new lows the West Texas Intermediate oil price hit back in April, when prices turned negative
This chart shows the new lows the West Texas Intermediate oil price hit back in April, when prices turned negative

Amid so much uncertainty, more users are turning to the FT to help them make sense of the markets. Using the new model built by the FT’s Data Science team, it is possible to work out the percentage of users who appear to be accessing the FT while making investment decisions.

This chart shows the proportion of users in the ‘making investment decisions’ mode in 2020, against the same weeks a year ago
This chart shows the proportion of users in the ‘making investment decisions’ mode in 2020, against the same weeks a year ago

With the model up and running, the Customer Analytics team have been able to look at trends for this user mode over time, and to overlay that with market data. When comparing the proportion of users in the ‘making investment decisions’ mode with the same day’s volume traded on the FTSE, the patterns do seem to align.

Chart showing the proportion of FT readers in ‘making investment decisions’ mode, overlaid with the volume of FTSE trading
Chart showing the proportion of FT readers in ‘making investment decisions’ mode, overlaid with the volume of FTSE trading

How it works

Although it is not possible to know for certain what a user’s intent is in visiting the FT, by building up profiles based on patterns of usage, visits can be segmented into meaningful groups.

“We started by considering research behaviour: looking for instances when a user is doing a deep dive on a specific topic, with the aim of improving their experience of this,” says Cloudy Carnegie. “For example, a user wanting to research a topic might want to be recommended old articles on the same topic, whereas a user in a news-browsing mode will be more focused on accessing up-to-date articles.”

“We then expanded the list to three other user modes: news-browsing, making investment decisions and sit-back reading — each of which involves users coming on site with a different aim.”

The models work by defining a set of features that can be measured in various combinations to identify the different modes. Some of the features include visiting the homepage, copying characters, or looking at markets data. Because many of these features overlap between different user modes, it is possible for a visit to be classified as falling under more than one mode.

Investing for the future

It is not particularly surprising that users are seeking investment information during times when markets have seen such extreme swings, but having the ability to identify this kind of behaviour could prove useful in understanding how best to serve users browsing with different purposes. Not every visit is for the same reason, so having an idea of trends and patterns can lay the groundwork for adapting the FT’s products to help users find more of what they are looking for.

The results of the models still need to be validated to make sure they are producing accurate data, and the plan is to do that in collaboration with the Customer Research team. But the initial results look promising.

FT Product & Technology

A blog by the Financial Times Product & Technology…

Jono Hutchison

Written by

FT Product & Technology

A blog by the Financial Times Product & Technology department.

Jono Hutchison

Written by

FT Product & Technology

A blog by the Financial Times Product & Technology department.

Welcome to a place where words matter. On Medium, smart voices and original ideas take center stage - with no ads in sight. Watch

Follow all the topics you care about, and we’ll deliver the best stories for you to your homepage and inbox. Explore

Get unlimited access to the best stories on Medium — and support writers while you’re at it. Just $5/month. Upgrade

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store