What are your users doing on your website or in your store? How do you turn the piles of data your organization generates into actionable information? Where do you get complementary data to make yours more comprehensive? What tech, and what techniques?
The Fifth Elephant is a two day conference on big data.
Early Geek tickets are available from fifthelephant.doattend.com.
The proposal funnel below will enable you to submit a session and vote on proposed sessions. It is a good practice introduce yourself and share details about your work as well as the subject of your talk while proposing a session.
Each community member can vote for or against a talk. A vote from each member of the Editorial Panel is equivalent to two community votes. Both types of votes will be considered for final speaker selection.
It’s useful to keep a few guidelines in mind while submitting proposals:
Describe how to use something that is available under a liberal open source license. Participants can use this without having to pay you anything.
Tell a story of how you did something. If it involves commercial tools, please explain why they made sense.
Buy a slot to pitch whatever commercial tool you are backing.
Speakers will get a free ticket to both days of the event. Proposers whose talks are not on the final schedule will be able to purchase tickets at the Early Geek price of Rs. 1800.
Recommendation Play @Flipkart
We will go over internet recommendation systems and how the user data can be mined to learn about preferences, tastes and behavior. The goal is to give users a flavor of building intelligent systems at scale.
Product discovery is an important step in users interaction with an ecommerce website and recommendation systems play a very useful part in the discovery process. Recommendation Systems aim to predict the user’s intent and help connect them to products they need or may be interested in. Recommending the right set of products for every user, understanding his intent and foreseeing the future requirements is very important. This becomes ever so important with increasing size of the catalog, making it harder for every user to express their intent through well formed queries.
In this talk we’ll motivate different ways in which recommendation systems simplify and enrich the discovery/decision process. We will talk about various types of recommendations and algorithms aimed at mining the collective intelligence from the users of our website. We will cover the challenges faced while building the flipkart recommendation system:
--Where to begin
--How and what data to collect from users
--Analyzing and understanding the above data to mine personal tastes and behaviour patterns
--Scaling challenges and achieving performance both at the frontend and the backend
Gaurav Bhalotia is the Director of Engineering for the Customer Platform at Flipkart. He has interest in information retrieval, search, categorization and related technologies and has several years of experience building scalable solutions around these. Prior to this he was leading teams at Kosmix (now @walmartlabs) and Retrevo building scaleable intelligent solutions.
Renuka and Pavan are the engineers behind Flipkart Recommendation System. They built the initial engine and have taken it through several improvements to a stage where it is a significant and important part of product discovery at Flipkart.
Renuka Khandelwal is SDE2 at Flipkart. Prior to joining Flipkart, she was with Siemens as Research Engineer in the Distributed System Team. Her major work is around Information Retrieval, Data Mining, Distributed Systems etc.
Pavan is working with Flipkart as SDE2. Prior to this, he was with Oracle working on the Security Framework for the Oracle Enterprise Manager. Post Graduated from IIT Madras, passionate to solve the complex algorithmic problems.