W6 L1 Flashcards
Recommendation Engines (RE) runs on
machine learning algorithms
pros RE and how (3)
RE enhance customer engagement, increase average order value, improve up/cross-selling opportunities by showing relevant productsthat are viewed or purchased together on the homepage and category pages.
Although there are multiple types, recommendation systems (filters) are usually categorized in two main kinds
(1) Collaborative <user> filtering models and (2) Content <item-product> based models.</item-product></user>
Recommendation Systems: 1 Content (Item) Based Filtering
example
“You bought this (X) you may also be interested in that (Y) – that is similar”
Content Based filter recommends
s a new product similar to purchased product
Content (Item) Based Filtering what is meant by preidentified
Similarities are pre-identified by the firm and/or analysts (comedy movie is considered as similar with another comedy movie)
Content (Item) Based Filtering disadvantage preidentified
What if she is a fan of the main actor – and mainly after his movies ?Do you see the problem with pre-identified similarity?
Meta Path is
A Meta Path is a sequence of relations between object types, which defines a new composite relation
why use meta paths
To improve the item (content) based recommendations and link with user based matching
3 steps meta path (or content based fileting)
(1) Pre-defined set of product characteristics: e.g. genre, writer, actors
(2) Calculate similarity between products > (3) Select the products that are most similar to the consumed products
pros content bassed filtering
Simple and intuitive. Useful even if we know nothing about the user (at cold start) and if we have little/no data on past purchases.
cons content bassed filtering
S: Not model based (is high product similarity a good recommendation?) Product characteristics hard to define – what is a similar product?
Collaborative (User Based) Filtering example
“People LIKE you also bought (saw) this….”
Collaborative (User Based) Filtering pros 2
: (1) Simple and intuitive (2) Takes into account user behavior
Collaborative (User Based) Filtering cons 3
(1) Not useful for users and products with few data (sparsity)
(2) Not useful for new users and products (cold start) (3) Computation time is large with thousands of users and products
Meta-Path based approaches combine
user feedback data with additional information, such as item or user attributes and
relationships. Therefore, they can emulate collaborative filtering, content-based filtering,
User-based framing
emphasizes the similarity between customers (e.g., “People who like this also like…”);
Item-based framing
g instead emphasizes similarities between products (e.g., “Similar to this item”).
Framing the same recommendation as USER-BASED (vs. item-based) can increase
recommendation click-through rates
Framing the same recommendation as USER-BASED (vs. item-based) can increase recommendation click-through rates. Espacially when: 3
(1) The customer is less experienced (2) attractiveness of the product is higher (3) and the user perceive the similarity with others as high
Recommenders: The Effect on Sales Diversity
Common Wisdom:
Recommender systems will help consumers discover new products by lowering their search costs
Recommenders: The Effect on Sales Diversity: a critical view
Collaborative filters (CFs)—will decrease sales diversity since they only reinforce the popularity of already well-known products
Use of collaborative filters (CFs) is associated with a decrease in sales diversity relative to no recommendations. when is this negative effeect stronger? and why
If the recommender is based on purchase data (rather than view data) this negative effect is stronger.
why: Similar users still end up exploring the same kinds of products, resulting in concentration bias at the aggregate level.
Human vs AI Recommender Utilitarian or Hedonic
AI recommenders are more competent than human recommenders in the utilitarian realm (utilitarian products) * AI recommenders are less competent than human recommenders in the hedonic realm (hedonic products)
Mobile Platforms have distinct characteristics that makes them different than non-mobile online 3
1 App-Based user interface
2 On-the-Go nature: Can be used in (physical) stores > bridging offline-online platforms
3 Different user characteristics, purposes and motivations / Different drives and consequences before/after usage
..% of customers purchase via mobile device in the last 6 months - ..% of all eCommerce purchases in 2018 were made on a smartphone
*80 eb 40
Search behavior vary depending on the device: non-mobile (desktop) vs mobile (smartphone and tablets) Higher CTR for
r tablets and desktop (> smartphones)
Search behavior vary depending on the device: non-mobile (desktop) vs mobile (smartphone and tablets) * Highest impression (%)
desktops > tablets > smartphones
Search behavior vary depending on the device: non-mobile (desktop) vs mobile (smartphone and tablets) When ad position (# - ranking) goes down:
almost no impression on smartphones. Thus it is important to have high ad position # on phones.
Smartphone conversion low = because
people use the device differently (seek information, start a journey etc.)
Time-of-Day Matters Search
tablet
desktop
Tablet traffic remained stable throughout the day and shows a peak around dinner time. * Desktop use/search is associated with day-time (working hours)
The impact of advertising is higher on mobile than on desktop. Why?
Higher consumer engagement (with ads) because there is far less advertising clutter on mobile,
Advertisements are delivered close to the actual point of purchase (geo-conquesting) —increasing relevance and impact.
Advertising clutter i
is the excessive amount of advertising messages customers receive every day
self/disclosing
willlingnes to reveal feelingd, thoughtd that are more personal
Consumers tend to be MORE SELF-DISCLOSING when generating content on
their smartphone versus personal computer.
increased self-disclosure smartphone arises from the psychological effects of two distinguishing properties of the device:
(1) Feelings of COMFORT that many associate with their smartphone
(2) Increased FOCUS ATTENTION on the disclosure task at hand due to the relative difficulty of generating content on the smaller device
Imagine a firm is about to launch a mobile-shopping app: What factors drives customers to download this app (more)?
Are these factors equally important for Free vs Paid apps ? How would their impact change/evolve over time ?
what is the first step to do
irst we have to distinguish between (i) Platform-Controlled vs User-Side variables and (ii) Free vs Paid apps.
pro of platform controlled
: impact of appearance in top apps charts stands out, especially early in a paid app’s lifecycle and throughout a free app’s.
what becomes more diffilcutl as apps mature
affecting the number of downloads becomes increasingly more difficult
what is hard and wat is influential when you just released an app
Gaining attention with users shortly after release seems critical and that app platform owners can be very influential in these early days
Mobile Shopping: To Have or Not to Have an App?
If you Already have a Mobile Website and why? 3
App adopters have higher purchase incidence, * App adopters buy more frequently, * App adopters spend more in each order than non adopters.
when are the effects of having an app strongen ? 2
These effects are stronger for (a) low spending customers (b) customer who are less loyal to retailer
Cross-Effects: Mobile App
Accessing the app increases sales especially online (which is not surprising) but increases OFFLINE sales as well.
why would you do paid version?
ps publishers generate cash flows in the early stage to recuperate initial costs,
a Free or Paid Version (or both) what works best
Offering both versions simultaneously helps achieve cost savings via economies of scale (at early stages)
Mobile push notifications are created by specific situations and instant (real-time) actions of customers: 4
Location / Whereabouts / Situation (i.e. jammed traffic) * Recent Behavior: clicks, views, purchases
* Time of the day: (i.e. back home from work) * Weather: rainy, snowy, sunny, warm or cold weather
Geofencing:
sending mobile ads to everyone in a visual fence at a certain time
Geotargeting
: send ads only to potential (certain) customers who are currently inside the “fence” or have been inside recently.
Geoconquesting
reaching customers who are considering your competitors (nearby competitors’ locations) and targeting them
Beaconing
involves the use of beacons - a small, physical object that receives location data from nearby devices (permission based and precise)
when use
Geofencing
Geotargeting
Geoconquesting
Beaconing
If you want to reach everyone in a certain area > Geofencing
If you want to certain people in a certain area (i.e. females) > Geotargeting
If you want to reach/engage with your competitors’ customer base > Geoconquesting
If you want to interact with your customers in your locations > Beaconing
Location-Based Targeting
Correct assessment of Mind-Set associated with the Current Location of the Customer
location based targeting: Messages are effective when the mobile ad message content fits the
e consumer mindset in each of two location contexts (home and work).
Highly personalized mobile messages may backfire by
eliciting consumer reactance
Location Based Mobile (Ad) efficacy depends on its potential to minimize consumer reactance, by effectively combining 3
1 Location targeting (in-store vs. outstore),
2 Behavioral targeting (based on consumers’ category involvement
3 Promotion offered (price vs. non-price promotion)
Combining Behavioral & Location Based (Mobile) Targeting most effective and when?
OVERALL: In-Store mobile ads are generally more effective in increasing sales than out-store mobile ads,
However: this is only the case if consumers have low involvement with the advertised product category because this decreases their reactance
To attract consumers to stores by Out-Store mobile targeting, firms should offer 2
price promotions to consumers with low category involvement * non-price promotions to consumers with high category inviolvement
Geo-Conquesting vs Geo-Targeting/Fencing what leads to increasing returns
Competitive local targeting (Geo-Conquesting)
Geo-Conquesting vs Geo-Targeting/Fencing what leads creating foot traffuc ans engagigng customers
Geo-Conquesting (targeting at competitors’ locations) can be as effective as Geofencing/targeting in creating foot-traffic and engaging customers
