Início Data Science no InfoQ Brasil
Apresentações
Feed RSS-
Utilizando o Apache Kudu como Workload Analítico
Um dos grandes desafios quando desenvolvemos um sistema de Workload Analítico em Tempo Real é trabalhar com dados que mudam de forma rápida em um intervalo de tempo muito baixo. A proposta dessa (...)
/presentations/utilizando-o-apache-kudu-como-workload-analitico/pt/mediumimage/Alan-Claudio_270-1516885672015.jpg)
-
Machine learning - Genesis ao Apocalipse
A palestra apresenta aspectos teóricos sobre aprendizado de máquina, estabelecendo um paradoxo com a ficção científica e as reais aplicações dessa tecnologia. A palestra apresenta as principais t(...)
/presentations/machine-learning-genesis-ao-apocalipse/pt/mediumimage/Everton-Robson_270-1514241236815.jpg)
-
The Panama Papers, Graphs and Data Science: Unravelling the Shady World of Offshore Finance One Data Structure at a Time
The Panama Papers – the world's largest leak of offshore data – exposed 2.6 terabytes in 11,5 million files spanning 40 years of records on more than 210k companies. In this talk we'll explore th(...)
/presentations/the-panama-papers-graphs-and-data-science/pt/mediumimage/Jim-Webber_270-1513732457973.jpg)
-
Billions and billions: using large-scale graph databases to detect financial fraud in real time
We'll discuss some use cases where financial services have used graph technology and the insights you get from connecting the facts in order to solve some billion-scale problems. To demonstrate t(...)
/presentations/using-large-scale-graph-databases-to-detect-financial-fraud-in-real-time/pt/mediumimage/Jim-Webber_270-1513169238623.jpg)
-
Feature Engineering: Extraindo o potencial máximo dos dados para modelos preditivos
Nesta palestra, serão apresentados métodos e técnicas que permitem extrair o potencial máximo das features de um dataset, aumentando flexibilidade, simplicidade e acurácia dos modelos. Serão abor(...)
/presentations/extraindo-o-potencial-maximo-dos-dados-para-modelos-preditivos/pt/mediumimage/Gabriel-Moreira_270-1510613446976.jpg)
-
A TenserFlow recommender system for news
Attending this presentation you're going to follow a detailed overview of how R&D team of Hearst's TV division is putting together Google BigQuery, Kubernetes cluster and Tensorflow to build a hy(...)
/presentations/a-tenserflow-recommender-system-for-news/pt/mediumimage/Fabricio-Vargas_270-1510576053285.jpg)
-
Improving customer value estimation by predicting conversion
The objective of this presentation is to describe the challenges of modeling a customer conversion predictor using real leads data observed on different levels of the conversion funnel. It will i(...)
/presentations/improving-customer-value-estimation-by-predicting-conversion/pt/mediumimage/Allan-Dieguez_270-1510007425882.jpg)
-
Big Data como Serviço: da captura à visualização de dados com alto desempenho
A Neoway fornece serviços de análise de dados e Big Data por assinatura, trabalhando com mais de 10 terabytes de dados indexados de centenas de fontes, em duas verticais: prospecção de clientes e(...)
/presentations/big-data-como-servico-da-captura-a-visualizacao-de-dados-com-alto-desempenho/pt/mediumimage/Kamila-Ricardo_270-1509399801442.jpg)
-
Learning from Data and Background knowledge
It is often possible to combine observed data with background knowledge, expressed as a set of rules or as a terminology. There has been significant work on the combination of data-centered metho(...)
/presentations/learning-from-data-and-background-knowledge/pt/mediumimage/Fabio-Cozman_270-1509410903375.jpg)
-
Building Machine Learning Service in your business
When making machine learning applications in Uber, we identified a sequence of common practices and painful procedures, and thus built a machine learning platform as a service. We here present th(...)
/presentations/building-machine-learning-service-in-your-business/pt/mediumimage/Eric-Chen_270-1508807987521.jpg)
-
Discovering hidden treasures in yout data with graph analytics
Companies data are most from DB and mined using traditional data mining approach. However, model relational data as a graph can reveal useful insights and discovery relation among data that is ig(...)
/presentations/discovering-hidden-treasures-in-yout-data-with-graph-analytics/pt/mediumimage/Ana-Appel_270-1508154267187.jpg)
-
Getting value from data science in the Telco business: the journey of Vivo Data Labs
In this presentation, we will go through the main challenges faced by the data scientists team since its creation and how we could leverage disruptive changes in our business process, technology(...)
/presentations/getting-value-from-data-science-in-the-telco-business/pt/mediumimage/Paula-Fadul_270.jpg)