November 2015 | AI Meetup: How Skimlinks uses Machine Learning to enrich pipeline

November 2015 | AI Meetup: How Skimlinks uses Machine Learning to enrich pipeline

We are the hosts of a regular artificial intelligence meetup called Applied AI, that showcases the latest and greatest in AI tech. Whilst they don't always have a theme, April's meetup showcased companies using AI in healthcare. If you'd like to learn more or join, please visit our meetup page

Skimlinks helps publishers to monetise their content. But the content that they receive from publishers can vary, meaning that their datasets are inconsistent or lacking in key data. Maria Mestre from Skimlinks looks into how machine learning can help.

Digital businesses have a variety of data sources, such as manually-curated data in relational databases and unstructured data coming from event logs. A common problem is how to leverage the information contained in the relational databases to enrich and augment the unstructured datasets. Using machine learning and big data tools such as Spark, it is possible to combine all these data sources. The talk will provide an example of a machine learning data ingestion pipeline using Spark.

Sign up for Ravelin Insights to get our best blogs straight to your inbox

More news you might like