Reading 2 Flashcards
Media effeciveness supports business growth by answering two key questions
1) what is the full impact of my media investments (capturing the full impact of your media investment by measuring:
All sales (online - including app- and offline
All media channels (digital and offline)
The short and long term impact on both sales and brands KPIs
2) How can I best optimize my media investments
Explore the relative value of different channel and campaign level strategies to enable frequent optimizations that continuously improve performance
Channel and campaign tactics
Budget allocation within a channel
Target goals per campaign
Testing of new formats and tactics
what are the key changes media mix modelling
Attribution: has reinvented itself to continue to prove real time data by relying on modelling to cover tracking gaps
Incrementality experiments are becoming more accessible and popular among advertisers thanks to more open source resources and increased availability to run experiments in platform
MMM is living a renaissance why
because of its future proof nature (it relies 100% on aggregated data) increased ability to show granular results, and improved frequency of updates
Overview of media effectiveness measurement tools: Data driven attributeion
The process of assigning credit to the different touchpoints that are found on a path to a conversation. Its fast and easy to scale, gives real time insight into drivers of performance, fuelling better automated bidding and optimisations at campaign channel and cross channel level. However is limited to digital channels and best suited for measuring short term impact. Requires large scale experiments to calibrate accurately. Is best used for daily channel and campaign optimisation
Overview of media effectivenss measurement tools: incrementality experiments
uses randomized and controlled experiments to compare the change in consumer behaviour between groups that are exposed or withheld from marketing activity while keeping all other factors constant. The goal standard to measure causlaity, so it gives the most rigorous view of the incremental value brought by the marketing investment. It gives a snapshot of a concrete strategy at a concrete point in time. Can be difficult to scale best used for adding an extra level of incrementaltiy awareness for your attribution and MMM efforts
MMM (media mix modelling)
Top level modelling that utilises advanced statistics to understand what drives sales. It measures media investment efficiency on top of base sales and other external faactors that impact sales. It gives a holistic overview of all channels, sales and external factors. it can also provide a longer term view of media impact. It does not require user level data, making it more future proof. It does require modelling with causal inference assumptions and at least two years of historical data. It can also be expensive to run. It is best used for cross channnel budget allocation
Popular models include (data driven marketing attribution)
Linear:credits an equal share of the payoff between all touch points
Time decay: credits a decreasing percentage of payoff the further away in time a touch point is from the date of conversion
Position: credits 40% to the first and last touches and the remaining 20 is evenly distributed to the touch in between
Game theory and shapely value
in a game of multiple players that can work together to increase the likelihood of a desired outcome (payoff), the shapely value provides a way to fairly divide the payofff between the players
Shapely value is a measure of a players average marginal contribution to each coalition. Taking into consideration that players can join coalitions at different points in time and have varying degrees of influence. Cooperative game theory and the shapely value provide a stable way to measure channel influence and fairly divide the credit for sales conversions between the channels, based on their individual contribution to the total payoff
Marketing benefits (data driven marketing attribution; shapely value )
Deeper insight into channel performance
Fair division of credit, based on measured contribution
Ability to optimize marketing investments and influence sales results
shapely value is a widely used and nobel prize winning solution (google analytics uses it for channel attribution)
The characteristics function
a game is defined by a set of players N and a characteristic function v. Every subset of player called a coalition S, and the characteristic function v(S) assigns a value to each coalition to signify its worth. A coalitions worth represents the payoff that it can generate when its players work together
Options for defining the characteristic function for marketing include:
Total revenue generated by each coalition
Total number of sales conversions generated by each coalition
Conversion ratio of each coalition
Conclusion on shapely value
it is clear from the shapely vlaues in this example that facebook is best performing channel, and the combination of facebook and linkedin is the most influential coalition. A CMO may look at this and decide to allocate more resources to facebook and linkedin to optimise conversion rates. They may also question why google is underperforming and invest more resources towards improving the campaigns running on google ads
Marketing attribution with markov
Marketing attribution
Marketing attribution: is a way of measuring the value of the campaigns and channels that are reaching your potential customer. The point in time when a potential customer interacts with a campaign is called a touchpoint, adn a collection of touchpoints forms a buyer journey
Limitations of traditional marketing attribution
all attribution models have their pros and cons, but one drawback the traditional models have in common is that they are rules based. The users has to decide up front how they want the credit for saels events to be divided between the touchpoints
Markov attribution models
Markov is a probabilistic model that represents buyer journeys as a graph, with the graphs nodes being the touchpoints or “states”, and teh graphs connecting edges being the observed transitions between those states
First state: webinar
Second state: ad click
example:
start 100 % webinar
20% campaign y = failure
42.5% campaign z = success
37.5% ad click –>
33.3% campaign y = failure
33.3 = success
33.3% = campaign zed = success
The markov graph can also tell us the overall succcess rate; that is, the likelihood of a successful buyer journey given the history of all buyer journeys. The success rate is a baseline for overall marketing performance and the need for measuring the effectiveness of any changes
