25
building intelligent data products

Building Intelligent Data Products (Applied AI)

Embed Size (px)

Citation preview

Page 1: Building Intelligent Data Products (Applied AI)

building intelligent data products

Page 2: Building Intelligent Data Products (Applied AI)

who am i? what does Ravelin do?

building intelligent data products

things to think about when building them

Page 3: Building Intelligent Data Products (Applied AI)

stephen whitworth

2 years at Hailo as data scientist/jack of some trades out of university

product and marketplace analytics, agent based modelling, data engineering, stream processing

services

data science/engineering at ravelin, specifically focused on our detection capabilities

Page 4: Building Intelligent Data Products (Applied AI)

what is ravelin?

online fraud detection and prevention platform

stream data to us

we give fraud probability instantly + beautiful data visualisation to understand your customers

backed by techstars/passion/playfair/amadeus/indeed.com founder/wonga founder amongst other great investors

Page 5: Building Intelligent Data Products (Applied AI)

fraud?

Page 6: Building Intelligent Data Products (Applied AI)

$14Blost in card not present fraud in 2014

a dollar for every year the universe has existed

Page 7: Building Intelligent Data Products (Applied AI)

Same day delivery On-demand services

Page 8: Building Intelligent Data Products (Applied AI)

‘victimless crime’

police ill-equipped to handle

low barrier to entry from dark net

3D secure - conversion killer

Page 9: Building Intelligent Data Products (Applied AI)
Page 10: Building Intelligent Data Products (Applied AI)

traditional: human generated rules, born of deep expertise

order-centric view of the world

Page 11: Building Intelligent Data Products (Applied AI)

hybrid: augment expertise by learning rules from data

cards don’t commit fraud, people do

stop the customer before they even get to ordering

Page 12: Building Intelligent Data Products (Applied AI)

‘a random forest is like a room full of experts who have seen different

cases of fraud from different perspectives’

Page 13: Building Intelligent Data Products (Applied AI)

‘a random forest is like a room full of experts who have seen different

cases of fraud from different perspectives’

N

Page 14: Building Intelligent Data Products (Applied AI)

measure and optimise for the right thing(s) in your data product

account for the fact that your customers are at different stages to one another, and optimise for different things

Page 15: Building Intelligent Data Products (Applied AI)

precision: of all of my predictions, what % was I correct?

recall: out of all of the fraudsters, what % did I catch?

implicit tradeoff between conversion and fraud loss

‘accuracy’ a useless metric for fraud

Page 16: Building Intelligent Data Products (Applied AI)

99.9% ACCURATE

Page 17: Building Intelligent Data Products (Applied AI)

use tools that make you disproportionately productive

shameless fans of BigQuery

our analysis stack: BigQuery, JupyterHub, pandas, scikit-learn

internal Google network is super fast, so wise to co-locate with your data

Page 18: Building Intelligent Data Products (Applied AI)

enable fast iteration by keeping model interfaces simple

hide arbitrarily complex transformations behind it

expose it over REST or a queue

version control them, roll backwards/forwards/sideways

Page 19: Building Intelligent Data Products (Applied AI)
Page 20: Building Intelligent Data Products (Applied AI)

q: do you always trade performance for explainability? a: no

if someone’s neck is on the line for your decision, allow them to understand how you came to it

Page 21: Building Intelligent Data Products (Applied AI)

RANDOM FORESTS

MONITORING

Page 22: Building Intelligent Data Products (Applied AI)

always be monitoring, probing for edge cases

dogfood - use robot customers

run strategies in ‘dark mode’ to determine performance

many ways things could break - be paranoid

‘machine learning: the high interest credit card of technical debt’ - Google

Page 23: Building Intelligent Data Products (Applied AI)

in beta and signing up clients

looking for on-demand services/marketplaces, payment service providers that are facing fraud

problems

talk to me afterwards

Page 24: Building Intelligent Data Products (Applied AI)

obligatory: we are hiring!

junior machine learning engineers/data scientists

[email protected] or talk to me after

Page 25: Building Intelligent Data Products (Applied AI)

[email protected] - @sjwhitworth

www.ravelin.com - @ravelinhq