market mix modelling in r.ppt€¦ · • from a market mix model, we know that advertising...

16
Market Mix Modelling in R Why aren’t more market mix modellers using R? Steve Cookson | May 2016

Upload: others

Post on 22-Jul-2020

1 views

Category:

Documents


0 download

TRANSCRIPT

Page 1: Market Mix Modelling in R.ppt€¦ · • From a market mix model, we know that advertising generated 5,000 units of sales, worth £100,000 • We also know that we spent £300,000

Market Mix Modelling in R

Why aren’t more market mix modellers using R?Steve Cookson | May 2016

Page 2: Market Mix Modelling in R.ppt€¦ · • From a market mix model, we know that advertising generated 5,000 units of sales, worth £100,000 • We also know that we spent £300,000

Market Mix Modelling in R

• My Background• Market Mix Modelling (MMM)

– What it is– Process & Output

• Why R is underused in MMM• 3 challenges to MMM that R can help with

Page 3: Market Mix Modelling in R.ppt€¦ · • From a market mix model, we know that advertising generated 5,000 units of sales, worth £100,000 • We also know that we spent £300,000

My Background

• Started Market Mix Modelling in 2005• Currently

My Mango Data Science Radar

Page 4: Market Mix Modelling in R.ppt€¦ · • From a market mix model, we know that advertising generated 5,000 units of sales, worth £100,000 • We also know that we spent £300,000

Data‐driven technique to measure the impact 

of marketing

Market Mix Modelling (MMM) Branch of Econometrics

Economics + Statistics

What is Market Mix Modelling?

Page 5: Market Mix Modelling in R.ppt€¦ · • From a market mix model, we know that advertising generated 5,000 units of sales, worth £100,000 • We also know that we spent £300,000

Gather Data

Market Mix Modelling (MMM) Branch of Econometrics

Economics + Statistics

Quantify drivers of a KPI – e.g. sales

Plug in financial data to calculate ROI

Budget Allocation

Stakeholder Questions

Page 6: Market Mix Modelling in R.ppt€¦ · • From a market mix model, we know that advertising generated 5,000 units of sales, worth £100,000 • We also know that we spent £300,000

Example Stakeholder Questions• Was my new product launch additive to the business or did it cannibalise?

• How does the stocking issue in Q2 affect our year‐end forecast?

• I have an additional $1MM budget.  Should I invest in Germany or Spain?

• Should I advertise Brand A or Brand B?

• Should I increase my % spend behind digital media?

• Should I stick with my new TV ad, or revert back to the old one?

• How did the cold weather affect our summer holiday campaign?

• Can I increase price or should I reduce?

Page 7: Market Mix Modelling in R.ppt€¦ · • From a market mix model, we know that advertising generated 5,000 units of sales, worth £100,000 • We also know that we spent £300,000

What data do you think we need for an MMM project?

• Can include (but not limited to):– KPI : usually sales– Media and/or marketing– Competitors– Climate– Holidays– Macro trends – e.g. economy– Stocking measures / shocks– Price and promotions

• Characteristics:– Over Time : Weekly, (Monthly, Daily or even Hourly)– Regional (where possible)

Page 8: Market Mix Modelling in R.ppt€¦ · • From a market mix model, we know that advertising generated 5,000 units of sales, worth £100,000 • We also know that we spent £300,000

MMM Methodology• Majority: Time Series, Multivariate Ordinary Least Square (OLS) Regression

– Explaining why a KPI like sales changes over time– Correlate multiple factors at once– Minimise the difference between the actual KPI and the modelled KPI– Look for stable models that make sense

• For equation fans:  yt = + x1t + x2t + … + ixit + t

Page 9: Market Mix Modelling in R.ppt€¦ · • From a market mix model, we know that advertising generated 5,000 units of sales, worth £100,000 • We also know that we spent £300,000

MMM Output• Modellers tend not to show the equation details to clients• Instead, we present the model graphically

-10

0

10

20

30

08-J

an-1

205

-Feb

-12

04-M

ar-1

201

-Apr

-12

29-A

pr-1

227

-May

-12

24-J

un-1

222

-Jul

-12

19-A

ug-1

216

-Sep

-12

14-O

ct-1

211

-Nov

-12

09-D

ec-1

206

-Jan

-13

03-F

eb-1

303

-Mar

-13

31-M

ar-1

328

-Apr

-13

26-M

ay-1

323

-Jun

-13

21-J

ul-1

318

-Aug

-13

15-S

ep-1

313

-Oct

-13

10-N

ov-1

308

-Dec

-13

05-J

an-1

402

-Feb

-14

02-M

ar-1

430

-Mar

-14

27-A

pr-1

425

-May

-14

22-J

un-1

420

-Jul

-14

17-A

ug-1

414

-Sep

-14

12-O

ct-1

409

-Nov

-14

07-D

ec-1

404

-Jan

-15

01-F

eb-1

501

-Mar

-15

29-M

ar-1

526

-Apr

-15

24-M

ay-1

521

-Jun

-15

19-J

ul-1

516

-Aug

-15

13-S

ep-1

511

-Oct

-15

08-N

ov-1

506

-Dec

-15

Sale

s (T

onne

s)

Week Ending

Brand XRegular Pr ice Stocking Market Seasonality & Compet it ion Advertising Promotions Volume

Page 10: Market Mix Modelling in R.ppt€¦ · • From a market mix model, we know that advertising generated 5,000 units of sales, worth £100,000 • We also know that we spent £300,000

MMM Applications• Price Elasticity :

– For every % increase in price, by what % will my sales fall ?• Rule of thumb: if the price elasticity < 1, then raising prices will increase profits

• Return on Investment (ROI) : – For every £1 I spent, how much did I get back in sales (or profit) ?– Example calculation:

• From a market mix model, we know that advertising generated 5,000 units of sales, worth £100,000• We also know that we spent £300,000 on advertising• So the ROI = £100,000 / £300,000 = 0.33

• Budget allocation :

Revenu

e

Spend

Revenue A Revenue B Revenue C

Page 11: Market Mix Modelling in R.ppt€¦ · • From a market mix model, we know that advertising generated 5,000 units of sales, worth £100,000 • We also know that we spent £300,000

MMM alternatives to R• Most market mix modellers don’t use R

• Either:

• Or MMM‐specific software:

• Or create their own software in‐house

Page 12: Market Mix Modelling in R.ppt€¦ · • From a market mix model, we know that advertising generated 5,000 units of sales, worth £100,000 • We also know that we spent £300,000

Why not R ?• Possible reasons?

– Economics graduates using E‐Views and STATA ?– Licensing issues ?

• Key issue: speed– Many MMM data sets are still small enough to manipulate in Excel

– Click and point is faster than command‐driven model building• CommandR package is basic

– Churn out standard MMM‐specific charts

Page 13: Market Mix Modelling in R.ppt€¦ · • From a market mix model, we know that advertising generated 5,000 units of sales, worth £100,000 • We also know that we spent £300,000

Can R help with challenges to MMM?

• Challenge #1‐ Explain the MMM results• Simply reporting ROI is not enough  • We must explain why ROI has changed

• One way involves storing models and their results• Run (cross‐sectional) meta‐analysis of modelling results

• R can store modelled results as variables / values for later use• R is better suited to cross‐sectional modelling than existing MMM software

Page 14: Market Mix Modelling in R.ppt€¦ · • From a market mix model, we know that advertising generated 5,000 units of sales, worth £100,000 • We also know that we spent £300,000

Can R help with challenges to MMM?

• Challenge #2‐ Forecasting and optimising

• Static reporting is not enough  • Clients are looking for scenario planning tools as standard

• R (via Shiny) can provide a direct link between models and an interactive output

Page 15: Market Mix Modelling in R.ppt€¦ · • From a market mix model, we know that advertising generated 5,000 units of sales, worth £100,000 • We also know that we spent £300,000

Can R help with challenges to MMM?

• Challenge #3‐ Alternative techniques                +

• MMM already exists in parallel to Digital Attribution and Single‐Sourcemodelling  

• These methodologies could merge in the future• Both use larger data sets than MMM and more complicated statistical techniques than Ordinary Least Squares (OLS)

• R can handle larger data sets / automated links• R is more versatile than existing MMM software – goes beyond OLS

Page 16: Market Mix Modelling in R.ppt€¦ · • From a market mix model, we know that advertising generated 5,000 units of sales, worth £100,000 • We also know that we spent £300,000

Thank You

Questions?