Designing IA for AI - Information Architecture Conference 2024
Vertical scrolling advertisement platform proximity sensor and beacon led intelligence
1. 1. Title : Vertical Scrolling advertisement Platform Proximity Sensor and beacon Led
Intelligence
2. Categories: Innovative Retail Future.
3. Summary:
Innovative Advertisement on your mobile directly picked up by mobile Bluetooth and
displayed like wall paper images on Mobile surface with offers.
1. In Store specific things.
Proximity sensor can Interact with beacon Carrying Store data for small store
2. All Super market aggregate things.
Proximity sensor can Interact with beacon near by Products data if you are inside store.
What is different here is approach: as you walk past Each store by store the banners will keep
changing of stores you are passing by.
4. Idea Description.
In-Store specific things:
When we carry a mobile near any Shop
having beacons Proximity Sensor should
display All The Articles of the store in kind
of running display like format shown
below
Above figure does reflect only one advertisement and not targeted but as shown below
we can display targeted advertisement in large grid. Each having 100 of items on
display. (Black flip shown below AJAX feature on one side flip book title on other side :
author price and other details event trigger it onTouch ).
For Example here we have book store: person walks past book shop in a mall.
See his mobile On screen he gets This display of book titles like (Banner Display works)
Here its is personalized banner display. Depending on like and searches by mobile
captured in during previous searches.
Two Kind of machine learning can be used here To get based on interest data we will discuss
(collaborative filtering, Content based Filtering).
For This Continuous data is gathered in app about phone passing each beacon. Beacon count
is increased on each successful pass and each touch will is sent for Content based Filtering
approach based on user history of preferences he can get more advertisement.
Simple approaches use the average values of the rated item vector while other sophisticated
methods use machine learning techniques such as Bayesian Classifiers, cluster analysis,
2. decision trees, and artificial neural networks in order to estimate the probability that the user
is going to like the item.
There is another panel : showing Unknown-Unknown Topics based on Collaborative
filtering of people with similar likings. collecting and analysing a large amount of
information on users’ behaviours, activities or preferences and predicting what users will like
based on their similarity to other users.
the k-nearest neighbour (k-NN) approach and the Pearson Correlation.
Collaborative Filtering is based on the assumption that people who agreed in the past will
agree in the future, and that they will like similar kinds of items as they liked in the past.
Using both Explicit(ask user to rate, search ,rank etc. ) or Implicit (analysing user viewing
times, analysing user social data ).
Advantage: Normally when we walk past banner Advertisement . Not only us there are
thousand people walking past it. So Today we have technology where big banners display
advertisement based on your mobile ID. Targeted advertisement.
Now When we see this pictures.
Around 1 banner we have atleast 100
people walking. Now if banner is
intelligent which Today’s banner are to
figure out advertisement to play based
on person near it.
But problem is which person it should
choose?
Even if chooses 1 person it looses
business from other 99 around it.
that is second problem.
To Solve this both problems we can
display advertisement as displayed on
mobile surface like shown in picture 1
for Book Titles to each person
depending on his previous interests and
searches called content based filtering, and some topics which are related but not known to
person of similar interest (collaborative filtering) (Or topics related to Unkonwn-Unknown as
they say in project management.)
Here it displays only one advertisement but actually we can display 100 in grid.
Proximity sensor can Interact with beacon Carrying Store data for small store and Product
data if you are inside store
For more detailed usage of Proximity sensors and Beacon Analytics you can read this case
study I have written long time back.