The Associated Press uses Machine Learning to automate writing of corporate financial reports
When Machine Learning meets journalism
Each year, companies in the United States have to produce corporate earnings reports. Those reports are then used by reporters from the Associated Press, to produce stories based on the published numbers. The stories would include company description, expert advice, facts, figures and all other details relevant to company performance.
It all started with a boring and mundane task
This article was written by the original story published here.
Producing corporate earnings recaps was an extremely time-consuming and mundane task. As mentioned by New York Magazine's Kevin Roose, compiling those reports was "a miserable early morning task that consisted of pulling the numbers off a press release, copying them into a pre-written outline, affixing a headline, and publishing as quickly as possible so that traders would know whether to buy stocks or not".
The Associated Press wanted to free the reporters to let them concentrate on producing more valuable content.
If the task is too boring, give it to a computer!
To solve the issue, the Associated Press used a Natural Language Generation platform - Wordsmith's API by Automated Insights - to turn data into insightful narratives. This API allows to transform data into a written text, insight personalised communications, recaps and so much more, saving loads of time, efforts and money.
Write more and better!
As a result, the Associated Press succeeded in producing over 4000 earnings reports per quarter compared to 300 reports (12 times more!) that were produced prior to this implementation. The implementation of automatically generated reports not only reduced the amount of time the reporters were spending on them but also reduced the number of errors in the reports increasing the overall efficiency of the internal processes.
MLab, the Machine Learning specialists at your service!
If Machine Learning inspires you and you think you would like to implement a use case in your organisation, please get in touch. We are vendor agnostic and we will recommend and integrate the technology that adapts the best to your needs. If non available technologies satisfy your needs, we can always train a custom model tailored to your project.
Disclaimer: MLab was not involved in the development of this project. We simply publish this case study in our blog as a source of inspiration on what Machine Learning can achieve.