Analyzing organization e-mails in near real time using hadoop ecosystem tools by Miguel Romero & Alberto de Santos at Big Data Spain 2015

Analyzing organization e-mails in near real time using Hadoop ecosystem tools

Session presented at Big Data Spain 2015 Conference
15th Oct 2015
Kinépolis Madrid
http://www.bigdataspain.org
Event promoted by: http://www.paradigmatecnologico.com
Abstract: http://www.bigdataspain.org/program/thu/slot-8.html#spch9.3

Transcript

2. © Copyright 2014 Hewlett-Packard Development Company, L.P. The information contained herein is subject to change without notice. Analyzing organization e-mails in Near Real Time using Hadoop Ecosystem tools Big Data Spain 2015 Miguel Romero, Hadoop Architect (@donkelito) Alberto de Santos, Data Scientist (@adesantossierra) Analytics and Data Management, Enterprise Services
3. © Copyright 2014 Hewlett-Packard Development Company, L.P. The information contained herein is subject to change without notice.
4. © Copyright 2014 Hewlett-Packard Development Company, L.P. The information contained herein is subject to change without notice. Un trabajador feliz se ausenta un 28,4% menos Un trabajador feliz es un 22% más productivo que uno infeliz $100,0 00
5. © Copyright 2014 Hewlett-Packard Development Company, L.P. The information contained herein is subject to change without notice.
6. © Copyright 2014 Hewlett-Packard Development Company, L.P. The information contained herein is subject to change without notice. Hacerm e su amigo ¿Redes sociales ? ¡Correo de empresa!
7. © Copyright 2014 Hewlett-Packard Development Company, L.P. The information contained herein is subject to change without notice. To/From To/From Asunto Asunto Contenido Contenido Adjuntos Adjuntos ¿Qué datos tengo?
8. © Copyright 2014 Hewlett-Packard Development Company, L.P. The information contained herein is subject to change without notice. ¿Qué grupos he encontrado? Entender quiénes envían/reciben más emails Usuarios más influyentes Detectar grupos de redes y entender sus características Analizar comunidades: cómo se forman, cómo se agregan integrantes Detectar evangelizadores Detectar expertos Mezcla de comunidades Hombres bisagra Agregación multiescala Normalized Cuts Max-flow min-cut algorithm To/From To/From Asunto Asunto
9. © Copyright 2014 Hewlett-Packard Development Company, L.P. The information contained herein is subject to change without notice. ¿De qué hablan en esas comunidades? To/From To/From Asunto Asunto
10. © Copyright 2014 Hewlett-Packard Development Company, L.P. The information contained herein is subject to change without notice. ¿De qué hablan en esas comunidades? To/From To/From Asunto Asunto
11. © Copyright 2014 Hewlett-Packard Development Company, L.P. The information contained herein is subject to change without notice. ¿De qué hablan en esas comunidades? To/From To/From Asunto Asunto
12. © Copyright 2014 Hewlett-Packard Development Company, L.P. The information contained herein is subject to change without notice. Online vs offline methods Detección de grupos ¿de qué se habla en cada grupo? Perfiles más influyentes Modelos clasificación Detección de anomalías Evolución de conversaciones Evolución de las comunidades
13. © Copyright 2014 Hewlett-Packard Development Company, L.P. The information contained herein is subject to change without notice.
14. © Copyright 2014 Hewlett-Packard Development Company, L.P. The information contained herein is subject to change without notice. Muchas gracias Big Data Spain 2015 Miguel Romero (@donkelito) Alberto de Santos (@adesantossierra) Analytics and Data Management, Enterprise Services