Lecture 2

Question 1

Measuring advertising response: How to evaluate the performance of marketing

Answer 1

Each campaign/channel evaluated on incremental profit that it produces relative to its cost

ROI = incremental profit due to advertising - cost of advertising/cost of advertising

Question 2

What are incremental sales and how do we measure them

Answer 2

Graph: Usual number of products sold and compare to products sold after the spend change

Additional sales made due to advertising over and above what would have been sold without advertising

Question 3

Incremental profit

Answer 3

Additional profit made due to advertising over and above what would have been sold without advertising

Typically: A function of incremental sales

Question 4

Popular techniques for estimating the incremental sales due to advertising:

Answer 4

This week: marketing attribute rules
Leveraging ability to track individual user data

Next week: Marketing mix modelling
With “aggregate” advertising spending and sales data

Later: Experimental approaches
Desinging “experiments” int he field to measure incrementality

Question 5

Conversion journies: the conversion to marriage

Answer 5

Online swipe -> coffee date -> movie date
-> proposal -> marriage

Question 6

Marketing attribution models: Marketing attribution

Answer 6

The process for determining which marketing touchpoint led to a conversion

Question 7

Attribution models

Answer 7

Are the rule, or set of rules, that determines how conversion credit is assigned to different marketing touchpoints

Question 8

How can I attribute credit to multiple campaigns that contributed to generating a conversion

The attribution problem assumes data on individual consumer journeys:
solution

Answer 8

rule based attribution

Data driven models

Question 9

touch attribution

Answer 9

A marketing effectiveness measurement technique that takes all of the touchpoints on the consumer journey into consideration and assigns fractional credit to each so that a marketer can see how much influence each channel has on sales

Question 10

Rule based attribution models

Answer 10

Use predefined rules and logit to assign credit to each touchpoint based on a certain assumption or criteria

Question 11

A single customer journey (rule based models)

Answer 11

track a single customer journey, Key performance indicator is sales

e.g. organic visit, online ad 1, online ad 2, online event, email offer, referal visit –> money

Question 12

Last touch attribution (rule based models) (last click)

Answer 12

Attribution looks backward from each conversion to find the last ad that the user saw (or clicked on) prior to the conversion

Question 13

Limitations of last touch

Answer 13

Mistakes when using last touch to estimate incremental sales

1. Other ads may have influenced customer and contributed to the sale
2. All sales are treated as incrementail
3. Unfairly favours channels that tend to show ads towards the end of path to purchase (such as search ads due to retargeting)

Question 14

When does last touch work?

Answer 14

Accurate measure of ad response when:

All sales are incremential
–> No sales wuld happen without the advertising

Effect of ads on behaviour is short-lived and ad exposure are spaced out over time

No “assists” from other advertising channels

Question 15

First touch (first click) attribution: Rule based models

Answer 15

Attrubution looks backward from each conversion to find the fist ad that teh user saw (or clicked on) prior to the conversion

Question 16

Linear attribution

Answer 16

Attribution looks backward from each conversion to find each ad that the user saw (or clicked on) prior to the conversion, assigning them equal weight

Question 17

Position based attribution (rule based models)

Answer 17

Attribution looks backward from each conversion to find each ad that the use saw (or clicked on) prior to the conversion, assigning higher weight to the first and last

Need to decide on what the higher weight is

Commonly seen: 30% or 40% for both first and last

Question 18

Time decay attribution (rule based models

Answer 18

Time decay attribution looks backward from each conversion to find each ad that the user saw (or clicked on) prior to the conversion, assigning higher weight to more recent ads.

Question 19

Limitations to rule based attribution

Answer 19

Rule based solutions are inflexible and unable to distinguish between the true low and high impact touch points

Leads to an incaccurate division of credit

Ignores all customers that dont convert

Analys/manager decides the attribution