Tree methods are among the most widely used algorithms in Machine Learning, due to their simplicity, their ability to capture non-linear relationships between variables, and their ease of use – they can deal with both numeric and categorical variables with no or little preprocessing.

Pablo J. Villacorta, Data Scientist at Stratio, will provide a review on these methods and the capabilities of Spark ML API to use distributed implementations in Big Data problems.

How much do you know about Kafka?

Stratio and Confluent begin a new collaboration to strengthen the Kafka community in Madrid. This will be the first of a serial of meetups we aim to celebrate each 2-3 months.

Agenda:

• Introduction to Apache Kafka… and why it matters! By Paolo Castagna, Senior Systems Engineer at Confluent. His background is on Big Data and he has first hand experience on the shift happening in the industry from batch to Stream processing and from Big Data to fast data.

  This talk will introduce Apache Kafka (including Kafka Connect, Kafka Streams APIs, and KSQL), Confluent, and explain why Apache Kafka is a great option and simplification for Stream processing in the context of two of the main driving forces and industry wide trends: Internet of Things (IoT) and Microservices.

• Kafka Use Cases on Microservices Architectures. On this talk, Óscar Gómez and Beatriz Pariente, Software Architects at Stratio, will show through real use cases how Kafka can help us on our event-driven Microservices Architectures.

Data Scientists are wild creatures who feed on data. Data Scientists are happy when there is plenty of data but they also suffer in a lot of occasions, mostly during the periods of data drought. In Darwinian terms, they compete for limited resources. Therefore, those Data Scientists that develop the best adaption strategies will survive (they will have good models) and those who don’t adapt in time will perish.

For a long time, Data Scientists comunis had been able to face this situation through data hunt and/or collection, but other also use cultivation and generation techniques of new data, providing stability to their models or balancing the classes. However, a whole new world of possibilities opens when new images enter in the menus of Data Scientists.

Together with Fernando Velasco, Data Scientist at Stratio, and Raúl de la Fuente, Presales at Stratio, we will study some ways to do this, using both classical techniques and Deep Learning. Will it be useful if we take the derivative of an image?