Trovit in short time became one of the leaders in the online classified advertising industry. We adopted Hadoop and MapReduce in order to manage all our content in a scalable way. However, we faced its limitations: that’s the reason why we looked at Spark. Right now, early 2016 we already adopted it for good and it is constantly bringing fresh solutions to our business. The talk will consist of an introduction to Trovit and its Big Data infrastructure, and we will specifically illustrate how Spark works with a demo.
Ferran Galí i Reniu is passionate about web scale distributed systems. Working on Big Data technologies for several years he gained expertise solving problems that require a massive amount of data processing. Architecting the deployment of Hadoop on a cluster of machines, developing new solutions or playing data scientist to make the business thrilling are some of the day-to-day tasks he has to deal with. Right now he is working in Trovit building the best search engine for classified ads.