applied data science: building a beer recommender | data science md - oct 2014

Post on 14-Jun-2015

727 Views

Category:

Data & Analytics

0 Downloads

Preview:

Click to see full reader

DESCRIPTION

Applied Data Science: Building a Beer Recommender | Data Science MD - Oct 2014 ----------- Slides from a talk by Greg Lamp, CTO of Yhat, about building recommendation systems using Python and deploying them to production.

TRANSCRIPT

Applied Data Science with Yhat

Greg Lamp

Data Science MD MeetupOctober 2014

1) Intro2) The Problem3) Solutions4) Case Study: Beer Recommender5) Demo6) Q/A

Here I am on the Internet.

Founder/CTO @ Yhat

Hi, I’m Greg!

Founders

Company

Investors

Greg Lamp, CTO

Austin Ogilvie, CEO

● Launched in 2013

● HQ in Brooklyn

Data sciencein the real world.

regression

Get Raw Data

Strategic Insights

Real World Scoring

Data Driven Products

Business Impact

Clean Data

Stages of the Analytics Project Life Cycle

Expert data teams

Management

Customers & Front Line Employees

What makes building analytical apps hard?

Hi, I’m Trey.

Meet Trey, the Data Scientist

We need to reduce churn.

Okay. I'll look into it.

I figured out that....some complex stuff about vector space that'll improve...

....and that's how we'll reduce churn.

Sounds good. Let's do that...

Any of you know what Gradient Boosting is?

So when can we go live with the new model?

Now what?

1)Translate Code

2 Rebel Policeme

n 2

2)PMML

?

3)Batch Jobs

use your tools

use your tools move quickly

use your tools move quickly

any workflow

use your tools move quickly

any workflow no translating

Case Study

+ =?

A Beer Recommender in Python

https://beers.yhathq.com

The Data

http://snap.stanford.edu/data/web-BeerAdvocate.html

Beers

Users

Ratings

Distance

vs

vs

calculating distance

eeny

? ?

eeny meeny

?

?Cosine

eeny meeny miny

?Cosine

moe

pick one.you can always

change

Thank you,

Scoring

Aggregate

Sort

Filter

Return

Deployment

What does this mean?

Import Yhat

Create a YhatModel

Define execute

Grab incoming data

Call your function

Format and return results

Demohttp://cloud.yhathq.com/http://beers.yhathq.com/

deploy your owngit@github.com:yhat/beer-rec.git

Python/R Source on githubIPython Notebook

Thanks!@yhathq

greg@yhathq.comyhathq.com

Questions?

top related