E-Metrics and E-Business Analytics Bamshad Mobasher School of Computing, DePaul University
Jan 05, 2016
E-Metrics and E-Business Analytics
Bamshad MobasherSchool of Computing, DePaul University
Bamshad MobasherSchool of Computing, DePaul University
2
Analyzing e-Customer Behavior In general, analyzing purchase behavior for online purchases is
similar to analyzing any purchase behavior, but we can do more on the Web
First it is possible and desirable to tie each purchase to an identified customer Can be done through Site registration information, shipping address, cookies,
credit card numbers
Some characteristics important for analyzing online purchases Frequency of purchases Average size of market basket Total number of different items purchased Total number of different item categories purchased Day of week and time of day Response to recommendations and online specials Comparison of online purchases to offline purchases
3
What We Want to Know Are we attracting new people to our site? Is our site ‘sticky’? Which regions in it are not? What is the health of our lead qualification process? How adept is our conversion of browsers to buyers? What behavior indicates purchase propensity? What site navigation do we wish to encourage? How can profiling help use cross-sell and up-sell? How do customer segments differ? What attributes describe our best customers? Can we target other prospects like them? What makes customers loyal? How do we measure loyalty?
4
Using Analytics for E-Business Management
Navigation Calibration Calculating Content Conversion Quotient Interaction Computation Customer Service Assessment Customer Experience Evaluation Branding
5
Analyzing e-Customer Behavior
Single Visit Behavior - what happens during a particular session or visit to the site:
Did the customer make a purchase? What pages did a customer visit prior to making a purchase? How many different products did a customer consider? How many different products did the customer purchase? How many different product categories did the customer visit? How many different product categories did the customer purchase? What ratio of the customer session was spent at pages containing products
that the customer purchased during this session? Is the shipping address the same as the billing address? If not, did the
customer request gift‑wrapping?
6
Analyzing e-Customer Behavior Multiple Visit Behavior - The ability to tie together customer behavior over
time is one of the key new capabilities enabled in the online world
Do customers first come to the site to browse and only then make purchases? This might suggest a segment of customers who compare prices before making a purchase.
Do customers who make repeated purchases broaden or narrow their purchase patterns? This might give insight into customer loyalty.
Do customers visit the site at relatively predictable intervals? This might give information about the time to next visit, so we can know when we need to start worrying because a particular customer has not been around for a while.
Over time, are repeat purchasers turning into more visitors, or are visitors turning more into repeat purchasers?
Are customers interested in the same categories every time they return to the site? This might suggest natural interest segments among customers.
Are there particular patterns among customers who have not returned in a long time? Were these customers one‑time purchasers? Did they purchase particular products? And so on.
Does responding to a special offer encourage customers to return?
7
Number of customers
Visits resulting in purchase
Average order value
Number of registered users
Origin of visitors
Customer service response time
Purchases over the last six months
Number of repeat visitors
Revenue for repeat visitors
Origin of repeat visitors
New and repeat conversion rates
Customers in a loyalty program
100%
95%
91%
88%
86%
79%
79%
74%
63%
63%
60%
47%
E-Metrics Commonly Used by Industry
Metrics That Sites Track and Analyze at Least Once a MonthSource: Jupiter Communications, 2000
8
The Goal of E-Business Analytics
E-Customer Life Time Value Optimization ProcessE-Customer Life Time Value Optimization Process
9
Reach
Acquisition
Conversion
Retention
Loyalty
Abandonm
ent
Attrition
Churn
Reactivatio
n
E-Customer Life Cycle Describes the milestones at which we:
target new visitors acquire new visitors convert them into registered/paying users keep them as customers create loyalty
10
Elements of E-Customer Life Cycle Reach
targeting new potential visitors can be measured as a percentage of the total market or based on other measures
of new unique users visiting the site
Acquisition transformation of targeting to active interaction with the site e.g., how many new users sessions have a referrer with a banner ad? e.g., what percentage of targeted audience base is visiting the site?
Conversion persuasion of browsers to interact more deeply with the site (registration,
customization, purchasing, etc.) conversion rate usually refers to ratio of visitors to buyers but, we need a more fine grained measure: micro-conversion rates
look-to-click rate click-to-basket rate basket-to-buy rate
Also: registration & customization ratios
11
Elements of E-Customer Life Cycle Retention
difficult to measure and metrics may need to be time/domain dependent usually measured in terms of visit/purchase frequency within a given time
period and in a given product/content category time-based thresholds may need to be used to distinguish between retained
users and deactivated-reactivated users
Loyalty loyalty is indicated by more than purchase/visit frequency; it also indicates
loyalty to the site or company as a whole special referral or “bonus” campaigns may be used to determine loyal
customers who refer products or the site to others in the absence of other information, combinations of measures such as
frequency, recency, and monetary value could be used to distinguish loyal users/customers
12
Elements of E-Customer Life CycleInterruptions in the Life Cycle
Abandonment measures the degree to which users may abandon partial transactions (e.g.,
shopping cart abandonment, etc.) the goal is to measure the abandonment of the conversion process micro-conversion ratios are useful in measuring this type of event
Attrition applies to users/customers that have already been converted usually measures the % of converted users who have ceased/reduced their
activity within the site in a given period of time
Churn is measured based on attrition rates within a given time period (ratio of
attritions to total number of customers goal is to measure “roll-overs’ in the customer life cycle (e.g., percentage
loss/gain in subscribed users in a month, etc.)
13
Untargeted PromotionsAttract Wrong People
Good TargetingIneffective Persuasion
Good PersuasionPoor Conversion
Good PersuasionGood Conversion
The Customer Life Cycle Funnel
Source: “E-Metrics Business Metrics For The New Economy,” NetGenesis, 2000.Source: “E-Metrics Business Metrics For The New Economy,” NetGenesis, 2000.
14
Basic E-Customer Life cycle Metrics
W (Target Market)
S (Suspects / Site Visitors)
P (Prospects / Active Investigators)
C (Customers)
CR (Repeat Customers)
NS
NP
CB (Abandon
Cart)
NC
CA(Attrited Customers)
C1(one-time Customers)
Note: Each of W, S, P, C and CR must be defined based on site characteristics and business objectives.
Note: Each of W, S, P, C and CR must be defined based on site characteristics and business objectives.
15
Micro-Conversion Rates
M1 (saw product impression)
M2 (performed product click through)
M3 (placed product in shopping cart)
NM1 NC
NM2 NC
NM3 NC
16
Micro-Conversion RatesP
M1 (saw product impression)
M2 (performed product click through)
M3 (placed product in shopping cart)
M4 = C (made purchase)
NP NC
NM1 NC
NM2 NC
NM3 NC
17
Basic E-Customer Metrics - RFM RFM (Recency, Frequency, Monetary Value)
each user/customer can be scored along 3 dimensions, each providing unique insights into that customers behavior
Recency - inverse of the time duration in which the user has been inactive
Frequency - the ratio of visit/purchase frequency to specific time duration
Monetary Value - total $ amount of purchases (or profitability) within a given time period
5 4 3 2 1
Recency 1 2 3 4 5Frequency
Mo
ne
tary
Va
lue
5 4
3 2
1
18
Basic Site Metrics Stickiness
measures site effectiveness in retaining visitors within a specified time period related to duration and frequency of visit
where
This simplifies to:
Stickiness = Frequency x Duration x Total Site ReachStickiness = Frequency x Duration x Total Site Reach
Frequency = (Visits in time period T) / (Unique users who visited in T)Frequency = (Visits in time period T) / (Unique users who visited in T)
Duration = (Total View Time) / (Unique users who visited in T)Duration = (Total View Time) / (Unique users who visited in T)
Total Site Reach = (Unique users who visited in T) / (Total Unique Users)Total Site Reach = (Unique users who visited in T) / (Total Unique Users)
Stickiness = (Total View Time) / (Total Unique Users)Stickiness = (Total View Time) / (Total Unique Users)
19
Basic Site Metrics Slipperiness
inverse of stickiness used for portions of the site in which it low stickiness in desired (e.g., customer
service or online support)
Focus measures visit behavior within specific sections of the site
Focus = (Avg. no. of pages visited in section S) / (Total no. of pages in S)Focus = (Avg. no. of pages visited in section S) / (Total no. of pages in S)
Either quick satisfaction orperhaps disinterest in this section.Further investigation required.
Either consuming interest on thepart of users, or users are stuck.Further investigation required.
Narrow Focus
Wide Focus
High Stickiness Low Stickiness
Attempting to locate the correctinformation.
Enjoyable browsing indicates asite ”magnet area”.
20
Using E-Metrics - Case of LandsEnd.com
Goals: Keep entire interactive team apprised of key metrics so that they make decisions and execute initiatives in concert and in real-time
Metrics tracked daily by LandsEnd.com Sales revenues Number of orders Average order values Total visits Revenues per visit Conversion rate Total page views Visits by source (e.g., entering URL directly, bookmark, e-mail,
referring site) Revenues by source (as above) Conversion rate by source (as above)
21
Using E-Metrics - Case of LandsEnd.com Not Enough
needed to cut each metric by new visitors and returning visitors, as well as new customers and returning customers
This led to the following additional metrics tracked daily: Percentage of traffic and page views from new vs. repeat visitors Average order from new vs. repeat customers Conversion rate for first-time visitors and customers Conversion rate for repeat visitors and customers Page views for new vs. repeat customers and visitors How much portals and affiliates are aiding in customer acquisition, and in
retention
The bottom line tracking the highest-level key metrics (traffic, revenues, average order)
day-to-day is standard operating procedure for commerce businesses distinguishing between behaviors of the first-time and repeat customers
allows the company to determine what constitutes the “trial” phase of the customer relationship, and how to move customers toward loyalty. Lands’ End does not consider somebody a “customer” until that person makes a second purchase
22
The CRM ‘Virtuous Circle’
Purchase response
Customer knowledge
Buying decision/proces
s
E-CRM – The case of Amazon.com
23
The continuing relationship …Amazon.com “Loyalty” model
Need CreationNeed Creation
Information search Information search
Evaluate alternatives Evaluate alternatives
Purchase transaction Purchase transaction
Post purchase experiencePost purchase experience
provide /assist
anticipate/stimulate
assist / negate
optimise /reward
add value
24
Need Creation (attract to website)
Need CreationNeed Creation anticipate/stimulate
25
Further Need Creation(upon reaching website)
26
provide /assistInformation searchInformation search
Information Search
27
Evaluation of Alternatives
assist / negateEvaluate alternativesEvaluate alternatives
28
Purchase Optimisation/Reward
optimise /rewardPurchase transaction Purchase transaction
•1-click purchase1-click purchase•‘‘slippery check out counter’ vs. ‘sticky aisles’slippery check out counter’ vs. ‘sticky aisles’
29
Post-purchase experience
add value Post purchase experiencePost purchase experience
30
Account Management
31
Is “loyalty” a relevant concept?
Amazon’s ‘customer lifetime value’ model (for book buyers) Average $50 for first time purchase Average $40 per visit thereafter Average of one visit per 2 months Assume customer will be active for 10 years
“4 buys and you are hooked” empirical law
32
Shopping Pipeline Analysis
Shopping pipeline modeled as state transition diagram Sensitivity analysis of state transition probabilities Promotion opportunities identified E-metrics and ROI used to measure effectiveness
Overall goal:•Maximize probability of reaching final state•Maximize expected sales from each visit
Enterstore
Browsecatalog
Selectitems
Completepurchase
cross-sellpromotions
up-sellpromotions
‘sticky’states
‘slippery’state, i.e.1-click buy
33
Additional Case Studies(Blue Martini Software)
MEC (Mountain Equipment Co-op) Canadian company selling sport and mountain
climbing gear leading supplier of quality outdoor gear and
clothing Consumer cooperative that sells to members only
DEBENHAMS Department store chain in UK 102 stores across the UK and Republic of Ireland
34
Bot Detection Significant traffic may be generated by bots Can you guess what percentage of sessions are generated
by bots?
23% at MEC (outdoor gear)
40% at Debenhams
Without bot removal, your metrics willbe inaccurate
More than 150 different bot families on most sites.
Very challenging problem!
35
Example: Web Traffic
Weekends
Sept-11 Note significant drop in human traffic, not bot
traffic
Registration at Search Engine sites
Internal Perfor-
mance bot
36
Search Effectiveness at MEC Customers that search are worth two times as much as
customers that do not search. Failed searches hurt sales
Visit
Search(64% successful)
No Search
Last Search SucceededLast Search Failed
10%90%
Avg sale per visit: 2.2X
Avg sale per visit: $X
Avg sale per visit: 2.8XAvg sale per visit: 0.9X
70% 30%
37
Referrers at Debenhams
Top Referrers
MSN (including search and shopping) Average purchase per visit = X
Google Average purchase per visit = 1.8X
AOL search Average purchase per visit = 4.8X
38
Page Effectiveness Percentage of visits clicking on different links
14% 13% 9% Top Menu 6%8%
Any product link 7%18% of visits exit at the welcome page
3%
3% 2% 2%
0.3% 2%2%2%
0.6%
39
Top Links followed from the Welcome Page:Revenue per session associated with visits
10.2X
1.4X 4.2X 1.4X Top Menu 0.2X 2.3X
Product Links 2.1X
10X
2.3X X 1.3X
5X
3.3X 1.7X 1.2X
Note how effective physical catalog item #s are
40
Product Affinities at MEC
Minimum support for the associations is 80 customers Confidence: 37% of people who purchased Orbit Sleeping Pad also purchased Orbit Stuff Sack Lift: People who purchased Orbit Sleeping Pad were 222 times more likely to purchase the Orbit Stuff
Sack compared to the general population
Product Association Lift Confidence
Orbit Sleeping Pad Cygnet
Sleeping Bag Aladdin 2Backpack
Primus Stove
OrbitStuff Sack
WebsiteRecommended Products
222 37%
Bambini Tights Children’s
Bambini CrewneckSweater Children’s
195 52%
Yeti Crew NeckPullover Children’s
Beneficial T’sOrganic LongSleeve T-Shirt Kids’
Silk CrewWomen’s
SilkLong JohnsWomen’s
304 73%
Micro Check Vee Sweater
VolantPants
Composite Jacket
CascadeEntrant Overmitts
Polartec300 DoubleMitts
51 48%
VolantPants
WindstopperAlpine Hat
Tremblant 575Vest Women’s
41
Product Affinities at Debenhams
Minimum support: 50 customers Confidence: 41% of people who purchased Fully
Reversible Mats also purchased Egyptian Cotton Towels Lift: People who purchased Fully Reversible Mats were 456 times more likely
to purchase the Egyptian Cotton Towels compared to the general population
Product Association Lift Confidence
WebsiteRecommended Products
J Jasper Towels
FullyReversibleMats
456 41%Egyptian CottonTowels
White CottonT-Shirt Bra
PlungeT-Shirt Bra 246 25%
Black embroidered underwired bra
Confidence 1.4%
Confidence 1%
42
Building The Customer Signature
Building a customer signature is a significant effort, but well worth the effort
A signature summarizes customer or visitor behavior across hundreds of attributes, many which are specific to the site
Once a signature is built, it can be used to answer many questions The mining algorithms will pick the most important attributes for
each question Example attributes computed:
Total Visits and Sales Revenue by Product Family Revenue by Month Customer State and Country Recency, Frequency, Monetary Latitude/Longitude from the Customer’s Postal Code
43
Migration Study - MEC
Oct 2001 – Mar 2002 Apr 2002 – Sep 2002
Migrators
Spent $1 to $200
Spent over $200
Spent over $200
Spent under $200
(5.5%)
(94.5%)
Customers who migrated from low spenders in one 6 month period to high spenders in the following 6 month period
44
Key Characteristics of Migrators at MEC
During October 2001 – March 2002 (Initial 6 months) Purchased at least $70 of merchandise Purchased at least twice Largest single order was at least $40 Used free shipping, not express shipping Live over 60 aerial kilometers from an MEC retail store Bought from these product families, such as socks, t-shirts, and accessories Customers who purchased shoulder bags and child carriers were LESS
LIKELY to migrate
Recommendation: Score light spending customers based on their likelihood of migrating and market to high scorers.
45
Customer Locations Relative to Retail Stores
Map of Canada with store locations.
Black dots show store locations.
Heavy purchasing areas away from retail stores can suggest new retail store locations No stores in several hot areas:
MEC is building a store in Montreal right now.
46
Distance From Nearest Store (MEC)
People farther away from retail stores
spend more on average
Account for most of the revenues
47
RFM Analysis (Debenhams)
Recommendation: Targeted marketing campaigns to convert people to repeat purchasers, if they did not opt-out of e-mails
Recommendation: Targeted marketing campaigns to convert people to repeat purchasers, if they did not opt-out of e-mails
Majority of customers have purchased once
More frequent customers have higher average order amount
Low Medium High Low Medium High
Anonymous purchasers have lower average order amount Customers who have opted out [e-mail] tend to have higher average order amount People in the age range 30-40 and 40-50 spend more on average
48
RFM for Debenhams Card Owners
Debenhams card ownersLarge group (> 1000)High average order amountPurchased once (F = 5)Not purchased recently (R=5)
Recommendation
Send targeted email campaign since these are Debenham’s customers. Try to “awaken” them!
Low Medium High Low Medium High
49
Consumer Demographics - Acxiom ADN – Acxiom Data Network Comprehensive collection of US consumer and telephone data
available via the internet Multi-sourced database Demographic, socioeconomic, and lifestyle information. Information on most U.S. households Contributors’ files refreshed a minimum of 3-12 times per year. Data sources include: County Real Estate Property Records, U.S. Telephone
Directories, Public Information, Motor Vehicle Registrations, Census Directories, Credit Grantors, Public Records and Consumer Data, Driver’s Licenses, Voter Registrations, Product Registration Questionnaires, Catalogers, Magazines, Specialty Retailers, Packaged Goods Manufacturers, Accounts Receivable Files, Warranty Cards
50
Consumer Demographics Using Acxiom, we can compare online shoppers to a
sample of the population People who have a Travel and Entertainment credit card are
48% more likely to be online shoppers (27% for people with premium credit card)
People whose home was built after 1990 are 45% more likely to be online shoppers
Households with income over $100K are 31% more likely to be online shoppers
People under the age of 45 are 17% morelikely to be online shoppers
51
A higher household income means you are more likely to be an online shopper
Demographics - Income
52
Demographics – Credit Cards
The more credit cards, the more likely you are to be an online shopper