The interconnection of devices within the ‘Internet of Things’ (IoT) enhances the empirical approach of Behavioural Science. It allows analysts to collect observational data and send personalised content to users. Also, practitioners can test more frequently which techniques are effective to alter behaviour. This talk presents three ways in which the ‘Internet of Things’ is being used to enhance the behavioural design. It shows how some practitioners, especially in financial services and marketing, are making use of the digital channels to optimise the activation and retention of users. In this sense, these channels not only help us to track our behaviour and personal goals but also provide a new framework that practitioners could follow when designing behavioural change interventions.
14. @michalkosisnski
“ Our smartphone, … , is a vast
psychological questionnaire that we are
constantly filling out, both consciously and
unconsciously. “
Michal Kosisnki
29. Subject groupings with Machine Learning
Bruges
Vienna
Verona
Bruges
Vienna
Verona
Romantic
Roman ruins
Photography
Historical-landmarks
Rhodes
Bayahibe
Kho Phi Phi
Diving
Snorkelling
Sun-bathing
Walking with kids
Lisbon
Sydney
Liverpool
Business
Shopping
Monuments
Diverse food
30. AB test with 34 Mi. users
Email marketing campaign
10% uplift in net conversion
31. Booking.com Booking Experiences app
Mobile-led experience
Personalised in-destination experience
Machine learning to predict individual traveller intent
All on demand, with hassle-free payment and priority queueing
32. What
Subfield in machine learning
Why
Learn a predictive preference
model
How
From observed behaviour
34. Impersonal default rules
“ Some of these rules do a great deal
of
good, but others might be poorly
chosen,
perhaps because those who select
them
are insufficiently informed, perhaps
because they are self-interested,
perhaps
because one size does not fit all. “
@CassSunstein
35. “ This report focuses on the more
automatic or context-based drivers
of behaviour, including the
surrounding ‘choice
environment’. “
@cabinetoffice
36. “ Attract attention. We are more
likely to do something that our
attention is drawn towards. Ways of
doing this include the use of images,
colour or personalisation. “
@B_I_Tweets
37. Data
BE
UX
“ Designing for behaviour change
integrates behavioural research,
pragmatic product development, and
rigorous data analysis. “
@sawendel
46. @GrowthTribe
Acquisition
Getting them to sign up
Activation
Users get a great first user experience
Retention
Making sure users come back
Referral
Getting users to invite others
Revenue
Sell, upsell, cross sell
Awareness
Getting people to visit your website
Conversion Funnel
@davemcclure
https://motherboard.vice.com/en_us/article/how-our-likes-helped-trump-win
Professor at Stanford University Graduate School of Business. Computational Psychologist and Big Data Scientist.
From July 2016:
Republican canvassers were provided with an app;
They could identify the political views and personality types of the inhabitants of a house;
Only rang at the doors of houses that the app rated as receptive to their messages;
Canvassers came prepared with guidelines for conversations tailored to the personality type of the resident;
Same app provider used by Brexit campaigners.
Democrats did similar things, but there is no evidence that they relied on psychometric profiling.
The firstcarquote Personality Quiz: firstcarquote has developed a personality quiz to help assess risk for new drivers because there’s a lot of scientific research that proves a link between an individual’s personality and their driving behaviour.
Why are we measuring these traits? There’s a growing body of scientific evidence that has found that these personality traits can be linked to driving risks, such as risky driving behaviour, driving style, traffic violations and crash risks.
Sources:
How Booking.com uses Machine Learning to Inspire Travellers
https://thosham.wordpress.com/2015/01/19/how-booking-com-uses-machine-learning-to-inspire-travellers/
Edwin Chen
http://blog.echen.me/2011/08/22/introduction-to-latent-dirichlet-allocation/
Noulas, A. and Einarsen, M. (2014) User Engagement Through Topic Modelling in Travel. Booking.com