Recommendations and Discovery at StumbleUponSumanth Kolar
RecSys 2012 Industry Track - Sumanth Kolar, StumbleUpon
It's human nature to be curious, to learn new things, to want to find out more. Discovery is an innate human need, and with the rise of the Web, the urge to learn more has increased by leaps and bounds. According to David Hornik, investor at August Capital, "The massive scale of the Web not only creates huge challenges for search, it also cripples discovery. Gone are the good old days in which fortuity would lead to the unearthing of interesting new websites." Indeed, we live in the age of "infovores" and there is definitely a need for a service that provides serendipity.
Providing serendipitous discovery that can inform, entertain and enlighten our users is of utmost importance to StumbleUpon. This talk will focus on how StumbleUpon uses several machine learning techniques such as collaborative filtering techniques, active learning, decision trees, Bayesian models and more to solve complex problems involving classification, user behavior analysis, modelling, anti-spam and recommendations. An average StumbleUpon user spends over 7 hours per month using the product, equating to hundreds of varied recommendations and ample feedback. The talk will also provide insights into some of StumbleUpon's rich data and how we can use scale to accomplish what would otherwise not be possible. We will look at innovative ways that StumbleUpon figures out the right metrics to evaluate recommender systems - a very complex problem. We will also discuss our research on StumbleUpon's mobile activity, which is growing 800% year over year and is the fastest growing part of our business, and how mobile recommendations are unique and important.
Bio: As Engineering Director at StumbleUpon, Sumanth Kolar leads the applied research team, overseeing recommendations, anti-spam, content analysis, user modeling, data sciences and infrastructure. ?Sumanth tackles very interesting and challenging research problems as StumbleUpon delivers more than 1 billion personalized recommendations a month to its more than 25 million users. Prior to joining the company in 2009, Sumanth engineered bidding and computer vision systems at Yahoo! and Adobe Research. Sumanth holds a masters degree in computer science from the University of California at Santa Cruz.
Creating a Global Engineering Culture - Agile india 2014Doc Norton
A short (and incomplete) telling of how we got to where we are as an engineering organization for Groupon. A little philosophy about what motivates individuals and teams. And finally a little bit about what we're doing at Groupon.
When it comes to creating a global culture, remember that you are more archeologist than architect. Uncover the good that is already happening and help to share it rather than trying to design something new.
What makes a 10X Engineer a class apart?Sumanth Kolar
10x engineers get shit done, think product, are great at collaboration, have amazing communication skills, lead by example, 10x the whole team, are always learning, keep things simple, act as an owner, are decisive about priorities and finally build to last.
Recommendations and Discovery at StumbleUponSumanth Kolar
RecSys 2012 Industry Track - Sumanth Kolar, StumbleUpon
It's human nature to be curious, to learn new things, to want to find out more. Discovery is an innate human need, and with the rise of the Web, the urge to learn more has increased by leaps and bounds. According to David Hornik, investor at August Capital, "The massive scale of the Web not only creates huge challenges for search, it also cripples discovery. Gone are the good old days in which fortuity would lead to the unearthing of interesting new websites." Indeed, we live in the age of "infovores" and there is definitely a need for a service that provides serendipity.
Providing serendipitous discovery that can inform, entertain and enlighten our users is of utmost importance to StumbleUpon. This talk will focus on how StumbleUpon uses several machine learning techniques such as collaborative filtering techniques, active learning, decision trees, Bayesian models and more to solve complex problems involving classification, user behavior analysis, modelling, anti-spam and recommendations. An average StumbleUpon user spends over 7 hours per month using the product, equating to hundreds of varied recommendations and ample feedback. The talk will also provide insights into some of StumbleUpon's rich data and how we can use scale to accomplish what would otherwise not be possible. We will look at innovative ways that StumbleUpon figures out the right metrics to evaluate recommender systems - a very complex problem. We will also discuss our research on StumbleUpon's mobile activity, which is growing 800% year over year and is the fastest growing part of our business, and how mobile recommendations are unique and important.
Bio: As Engineering Director at StumbleUpon, Sumanth Kolar leads the applied research team, overseeing recommendations, anti-spam, content analysis, user modeling, data sciences and infrastructure. ?Sumanth tackles very interesting and challenging research problems as StumbleUpon delivers more than 1 billion personalized recommendations a month to its more than 25 million users. Prior to joining the company in 2009, Sumanth engineered bidding and computer vision systems at Yahoo! and Adobe Research. Sumanth holds a masters degree in computer science from the University of California at Santa Cruz.
Creating a Global Engineering Culture - Agile india 2014Doc Norton
A short (and incomplete) telling of how we got to where we are as an engineering organization for Groupon. A little philosophy about what motivates individuals and teams. And finally a little bit about what we're doing at Groupon.
When it comes to creating a global culture, remember that you are more archeologist than architect. Uncover the good that is already happening and help to share it rather than trying to design something new.
What makes a 10X Engineer a class apart?Sumanth Kolar
10x engineers get shit done, think product, are great at collaboration, have amazing communication skills, lead by example, 10x the whole team, are always learning, keep things simple, act as an owner, are decisive about priorities and finally build to last.
1. Conformación del equipo
del semillero 5: “Científicos
de la tecnología” de 7°F
Juegos de
razonamiento
matemáticos
Lluvia de ideas
Con detonadores de parque
explora - categorías
Aprendizaje desde
los videos de apoyo
L.U.P
Listado único
de palabras
30 preguntas de
investigación (10
preguntas mejores)
Aplicación de las 4 categorías de Expo
1. Investigación
2. Demostración de principios
3. Servicios públicos
4. Innovación.
Cuadro de
valoración de los
problemas
(5 criterios)
5 CRITERIOS DE VALORACION
1. Factibilidad
2. Costo
3. Tiempo
4. Innovación
5. Solución tecnológica
Elección de las 5
mejores preguntas
de investigación.
Descartar 4
preguntas
Pregunta
reina de mi
investigación
Pasos de la
investigación
Refinar la pregunta de
investigación
Identificación del
problema
Diseño de la
investigación
Definir el método y
proceso de la
investigación
Instrumentos:
*Entrevista
*Ensayos
*Encuestas
Simulacros
*Recopilación de datos
* Análisis de Datos
Proyecto textual:
1. Anteportada
2. Portada
3. Titulo
4. Justificación
5. Objetivo general
6. Objetivos
específicos
7. Marco teórico
8. Marco
metodológico
9. Instrumentos de
Inv.
10. Variables
11. Trabajo de campo
12. Hallazgos
13. Posibles soluciones
Solución tecnológica y
construcción a prueba
Análisis del objeto y/o Sistemas
Proyecto textual (Completo)
Planos y diseños
“ de la mente al papel”
Construcción final del art.
Conclusiones y análisis
Exposición frente a la
Comunidad Educativa
de la IETISD
Participación en Ferias y eventos
Tecnológico-científicos: IETISD, EXPLORA, ALIANZA
ONDAS, CORUM, SENA