28:54
EY Aleph: deep learning applied to jurimetrics practice
The jurimetrics practice in Brazil, when exists, usually is done with local data from legal offices using data collected from its own cases using time-consuming manual processes. Our approach is(...)
44:45
Architecture of an NLP Deployment
This talk explores the deployment of machine learning models as part of a larger system. The existing environment has an influence on available options. We will look at the different functional c(...)
27:49
Hindsight bias: A machine learning story
In this session, you'll learn about data leakage (aka label leakage) challenges while building Salesforce Einstein and the methods we used to detect and fix them automatically.
39:49
Panel: Kaggle as stepping stone for a Data Scientist career
In this panel we will see a talk about data science competitions and how this can change your career.
29:58
Ciência de dados no mundo real com Serenata de Amor
É possível fazer ciências de dados no mundo real? Conheça mais sobre a Serenata de Amor, projeto que enfrentou todas as dificuldades de lidar com dados abertos governamentais e mostrou que é poss(...)
42:37
Data Lake além da buzzword
O objetivo dessa palestra é compartilhar os erros e acertos na implantação de um Data Lake através da análise de trade-offs e resultados de benchmarks realizados durante a jornada na Movile. Util(...)
36:33
Deep Recommender Systems
In this talk, you will understand the big picture of state-of-art RecSys techniques based on DL. We’ll present a practical example of News Recommendation implemented with Tensorflow. We’ll also i(...)
51:12
Navigating Distributed Traces
Building off Jaeger's open source distributed tracing system, we designed XYS to allow for interactive exploration of inter-service latency histograms and to directly connect long tail latency me(...)
44:43
Recomendação de conteúdo na escala do iFood
Nesta palestra vamos apresentar os desafios relacionados a recomendação de conteúdo na escala do iFood e como temos trabalhado para aumentar a personalização do seu aplicativo. Serão abordados te(...)
44:32
Validating Big Data Jobs - Stopping Failures before Production (w/ Spark, BEAM, & friends!)
The talk will have code examples in Apache Spark, as well as explore similar concepts in Apache BEAM (a cross platform tool), but the techniques should be applicable across systems. To keep the t(...)
22:32
Extracting Entities and Relations in Portuguese Documents
This talk describes an application developed to interpret documents, extracting important information. A pipeline of machine learning models comprising Named-Entity Recognition and Relation Extra(...)
48:39
Experimentações com grandes volumes de dados usando Notebooks
Notebooks são ferramentas usadas em Data Science que permitem a criação de documentos na web que integram código, gráficos, animações e textos possibilitando a criação de narrativas capazes de co(...)
