Media mix: Difference between revisions
From CEOpedia | Management online
m (Infobox update) |
m (Text cleaning) |
||
| (2 intermediate revisions by 2 users not shown) | |||
| Line 1: | Line 1: | ||
'''Media mix''' is a '''statistical model''', that allows to foresee what will the future amount of sales be with the said level of investemnt made in that moment. Their history reaches the 1960s and since then, they've been useful to advertisers from all around the world. In its functionality, it uses aggregated data from the past to come up with a model that will show the sales outcome with the [[marketing]] derivatives, advertising derivatives and other derivatives, like seasons, weather, etc. The model helps to understand the effectiveness of the advertiser's [[work]] in driving sales so that the budget is allocated in as optimised way as possible<ref>Chan D., Perry M. (2017). [https://static.googleusercontent.com/media/research.google.com/pl//pubs/archive/45998.pdf ''Challenges And Opportunities In Media Mix Modeling.''] Google Inc. </ref>. Media mix model analysis is needed also, because the clients are nowadays much tougher to reach and please than before. The [[technology]] and media they use result in their [[need]] of effectiveness and results reports coming from the [[company]]<ref>Magazine Publishers of America. (2005) [http://www.customores.com/ad_blues/Accountability_Study.pdf ''Accountability: A Guide to Measuring ROI and ROO Across Media. A Resource for Advertisers, Agencies, Marketing and Media Professionals''] "Accountability: A Guide to Measuring ROI and ROO Across Media"</ref> | |||
'''Media mix''' is a '''statistical model''', that allows to foresee what will the future amount of sales be with the said level of investemnt made in that moment. Their history | |||
==Data used in the media mix model== | ==Data used in the media mix model== | ||
| Line 30: | Line 13: | ||
* Distinction of a relative variable - making the variables comparable and similar in their correlation level; | * Distinction of a relative variable - making the variables comparable and similar in their correlation level; | ||
* Subproblem division of classes - dividing existing problem into the general ones, that affect the whole company and the ones of the subbrands, that do not affect anything beside the subbrand itself; | * Subproblem division of classes - dividing existing problem into the general ones, that affect the whole company and the ones of the subbrands, that do not affect anything beside the subbrand itself; | ||
* Different level phasing of variables - classification of the variables and showing their dependence and influence on others. | * Different level phasing of variables - [[classification]] of the variables and showing their dependence and influence on others. | ||
==Footnotes== | ==Footnotes== | ||
<references/> | <references/> | ||
{{infobox5|list1={{i5link|a=[[Geodemographic segmentation]]}} — {{i5link|a=[[Customer analysis]]}} — {{i5link|a=[[Media strategy]]}} — {{i5link|a=[[Demographic variables]]}} — {{i5link|a=[[Market metrics]]}} — {{i5link|a=[[Customer profile]]}} — {{i5link|a=[[Deceptive advertising]]}} — {{i5link|a=[[Measuring of advertising effectiveness]]}} — {{i5link|a=[[Sales trend]]}} }} | |||
==References== | ==References== | ||
Latest revision as of 00:45, 18 November 2023
Media mix is a statistical model, that allows to foresee what will the future amount of sales be with the said level of investemnt made in that moment. Their history reaches the 1960s and since then, they've been useful to advertisers from all around the world. In its functionality, it uses aggregated data from the past to come up with a model that will show the sales outcome with the marketing derivatives, advertising derivatives and other derivatives, like seasons, weather, etc. The model helps to understand the effectiveness of the advertiser's work in driving sales so that the budget is allocated in as optimised way as possible[1]. Media mix model analysis is needed also, because the clients are nowadays much tougher to reach and please than before. The technology and media they use result in their need of effectiveness and results reports coming from the company[2]
Data used in the media mix model
Media mix model is usually prepared for the advertiser by a third-party company that takes all of the needed aggregated data that is supplied by the advertiser. This data, collected either weekly or monthly, consists most usually of national data, but sometimes geo-level data or even store-level data can be used as well - the results will still be measurable. No matter which level of data is needed and supplied, all of them include[3]:
- Response data - the data which shows the direct effect of the work, wuthout any other derivatives that will give the information whether it is a good result or a bad result. Usually, this piece of data includes sales, but it can also be some other derivatives: store visits or KPIs;
- Media metrics - statistical data from the media channes used by the marketing department in the advertiser's company. It usually includes such popular and easy to collect data as clicks and impressions, along with the most common media spend;
- Marketing metrics - the 4 P's of the company: price, product, promotion and place (distribution) information;
- Control factors - seasonality, weather and market competition.
Four steps of implementing media mix
When a company wants to include media mix model results in their strategy, these are steps that need to be followed[4]:
- Variable clustering - testing the variables important for the media mix model and their effect on the market;
- Distinction of a relative variable - making the variables comparable and similar in their correlation level;
- Subproblem division of classes - dividing existing problem into the general ones, that affect the whole company and the ones of the subbrands, that do not affect anything beside the subbrand itself;
- Different level phasing of variables - classification of the variables and showing their dependence and influence on others.
Footnotes
- ↑ Chan D., Perry M. (2017). Challenges And Opportunities In Media Mix Modeling. Google Inc.
- ↑ Magazine Publishers of America. (2005) Accountability: A Guide to Measuring ROI and ROO Across Media. A Resource for Advertisers, Agencies, Marketing and Media Professionals "Accountability: A Guide to Measuring ROI and ROO Across Media"
- ↑ Chan D., Perry M. (2017). Challenges And Opportunities In Media Mix Modeling. Google Inc.
- ↑ Sharma P., Meena M. J., Ibrahim Sp S. (2017) Media Mix modeling comparison of interaction model to simple log-linear model "Asian Journal of pharmaceutical and clinical research"
| Media mix — recommended articles |
| Geodemographic segmentation — Customer analysis — Media strategy — Demographic variables — Market metrics — Customer profile — Deceptive advertising — Measuring of advertising effectiveness — Sales trend |
References
- Chan D., Perry M. (2017). Challenges And Opportunities In Media Mix Modeling. Google Inc.;
- Magazine Publishers of America. (2005) Accountability: A Guide to Measuring ROI and ROO Across Media. A Resource for Advertisers, Agencies, Marketing and Media Professionals "Accountability: A Guide to Measuring ROI and ROO Across Media";
- Sharma P., Meena M. J., Ibrahim Sp S. (2017) Media Mix modeling comparison of interaction model to simple log-linear model "Asian Journal of pharmaceutical and clinical research"
Author: Olga Muryn
