BM05MM MARKETING STRATEGY RESEARCH
1 INTRODUCTION
LECTURE 25-10-2021
SECTION 1: Introduction
Premise:
- Already have a clean dataset!
- Idea: we have consumers and then collect data (=abstraction of actual consumers)
Process:
- Cleaned data → generate insights → guide strategic decision making
- Data driven strategy!!
- How do we do this? → with TOOLS (focus of this course!)
Xi Chen, expertise:
- Quantitative marketing
- Digital marketing
- Policy evaluation
- Rich experience with data analysis
Vb. Charlie Temple (glasses store) -> sell this only online! No physical stores, no services etc, therefore they can
reduce the price. They have AR (augmented reality) in the digital fitting room.
Terms related to marketing analytics:
- CTA/ CTR/ CPC
- SEO/ SEA
- Google Analytics
- AB testing
- Data scraping
More availability of online data! Therefore more interesting to do (online) marketing analytics.
How frequently marketing analysis are used in companies?
- Availability of data → more time invested in marketing analytics → used in decision making
SECTION 2: Overview of the course
Marketing research process
DATA → TOOLS → STRATEGY
What kind of tools?
- 150 tools in 2011
- 8.000 tools in 2020!
- Choose which one is useful in your research
,Emphases:
- “Hands on” analytic experiences → too many technologies, we don’t know what works. Work with
real life data and cases
- Data analytics for insights & strategy
- Principles for “post-school” learning
o Principle 1
o Principle 2
o Principle 3… etc
Learn the principles behind marketing analytics which are useful in your future career with new
technologies. More focussed on insights and guidelines instead of specific technologies.
TOOLS:
1. Linear regression → market responses models
2. Bass model → new product diffusion
3. Conjoint analysis → product innovation (preferences elicitation)
4. Cluster analysis → segmentation (targeting and positioning)
5. Multi-dimensional scaling → positioning (how you are related from competitors, differentiated in the
market)
Learning objectives:
- Get hand on experiences with marketing analytics
- Understand the concept of data-drive marketing strategy
- To formulate of a framework of “when” and “how” to use a new analytic tool
Practical objectives:
- Get tools for thesis
- Make sure you understand the basics and move forward from this
Challenges:
- Diversities in group & class size
- Statistics is challenging -> not learn the mathematics, but the principles
- Online learning
Overview:
Session 2 = marketing response analysis
Session 3 = bass model
Session 4 = conjoint analysis
Etc..
Adapt blended learning → lectures on Monday:
- Basic concepts
- Systematic way of implementation
, - Interpretation of R outputs
- Limitations of tools
Principles of blended learning lectures:
- Principles of statistical analysis and marketing analytics
Recorded and posted on Canvas!!
Practical sessions → every Tuesday
- Learn how to analysis in R
- Try to get your hands dirty
Procedure practice sessions and R tutorials
- Xi will do a tutorial in first 30 minutes
- Tas available
- Tutorial videos are shared after class
3 sessions R tutorials:
- Section 1 = my tutorial (30 minutes)
- Section 2 = your practises (check R notebooks, replicate the results, think about how to run the
analysis)
- Section 3 = tutorial videos (5-10 minutes)
Case discussions: on Wednesdays
- Key methods to link analytics with marketing insights and strategies
- Data-driven (may be very different from general case discussion)
- For quality of case discussions, we split into two sections
- Twice the same contents
- Time:
o Group 1 = 13-14:45
o Group 2 = 15:00-16:45
SECTION 3: Case discussion
“Jetstar” example, background:
- Competing of two cheap airlines → analyse consumer preferences! What kind of factors are
influencing choices for cheap flights
- Opportunities for analytics?
- Marketing goals of analytics?
- Which tools to apply?
In the end: strategy recommendations
- How to formulate strategies based on analytical results?
ASSESSMENT
Sign up in duo’s! → Groups sign up on canvas.
, 2 types of questions
- Analysis & interpretation
- Conceptual or managerial questions
Each 15% → 2 assignments of session 3 and session 6 → 10 days to work on the assignment!
Exam (70%) → offline and two-hours → December 20th
Analytics + questions
- Conceptual questions and interpretation of R output
- Exemplary questions will be posted on BB in due time
CLOSED BOOK EXAM!!!
You get output -> explain and interpret. Little bit calculation (bring calculator!!), some ethics questions,
compare different methods (conceptual). No statistical mathematic included at all!
Exam on paper!! NOT online!
Group 2!! For discussion groups. Group 2 = 15:00-16:45
2 MARKET RESPONSE MODEL
LECTURE 1-11-2021
Structure this week:
- Lecture = Monday
- Tutorials = Tuesday
- Case discussion = Wednesday
SECTION 1: Agenda
1. Linear regression! -> use predictive modelling
2. Making assumptions -> how to do it? And how to check the assumptions? What to do when
assumptions are violated
Video: target knew teen was pregnant before her dad
- Computer model: finding out behaviour in shops which predicted pregnancy. VB. lotion in large
quantities
- Baby ads looked random -> habits matter -> predicting consumer behaviours
SECTION 2: Prediction and linear regression
Description of a prediction machine:
Feed machine with data → put in the machine → get prediction
Objective = to find functional relationship between input (variables) and output (something you want to
predict).
Prediction machines:
1 INTRODUCTION
LECTURE 25-10-2021
SECTION 1: Introduction
Premise:
- Already have a clean dataset!
- Idea: we have consumers and then collect data (=abstraction of actual consumers)
Process:
- Cleaned data → generate insights → guide strategic decision making
- Data driven strategy!!
- How do we do this? → with TOOLS (focus of this course!)
Xi Chen, expertise:
- Quantitative marketing
- Digital marketing
- Policy evaluation
- Rich experience with data analysis
Vb. Charlie Temple (glasses store) -> sell this only online! No physical stores, no services etc, therefore they can
reduce the price. They have AR (augmented reality) in the digital fitting room.
Terms related to marketing analytics:
- CTA/ CTR/ CPC
- SEO/ SEA
- Google Analytics
- AB testing
- Data scraping
More availability of online data! Therefore more interesting to do (online) marketing analytics.
How frequently marketing analysis are used in companies?
- Availability of data → more time invested in marketing analytics → used in decision making
SECTION 2: Overview of the course
Marketing research process
DATA → TOOLS → STRATEGY
What kind of tools?
- 150 tools in 2011
- 8.000 tools in 2020!
- Choose which one is useful in your research
,Emphases:
- “Hands on” analytic experiences → too many technologies, we don’t know what works. Work with
real life data and cases
- Data analytics for insights & strategy
- Principles for “post-school” learning
o Principle 1
o Principle 2
o Principle 3… etc
Learn the principles behind marketing analytics which are useful in your future career with new
technologies. More focussed on insights and guidelines instead of specific technologies.
TOOLS:
1. Linear regression → market responses models
2. Bass model → new product diffusion
3. Conjoint analysis → product innovation (preferences elicitation)
4. Cluster analysis → segmentation (targeting and positioning)
5. Multi-dimensional scaling → positioning (how you are related from competitors, differentiated in the
market)
Learning objectives:
- Get hand on experiences with marketing analytics
- Understand the concept of data-drive marketing strategy
- To formulate of a framework of “when” and “how” to use a new analytic tool
Practical objectives:
- Get tools for thesis
- Make sure you understand the basics and move forward from this
Challenges:
- Diversities in group & class size
- Statistics is challenging -> not learn the mathematics, but the principles
- Online learning
Overview:
Session 2 = marketing response analysis
Session 3 = bass model
Session 4 = conjoint analysis
Etc..
Adapt blended learning → lectures on Monday:
- Basic concepts
- Systematic way of implementation
, - Interpretation of R outputs
- Limitations of tools
Principles of blended learning lectures:
- Principles of statistical analysis and marketing analytics
Recorded and posted on Canvas!!
Practical sessions → every Tuesday
- Learn how to analysis in R
- Try to get your hands dirty
Procedure practice sessions and R tutorials
- Xi will do a tutorial in first 30 minutes
- Tas available
- Tutorial videos are shared after class
3 sessions R tutorials:
- Section 1 = my tutorial (30 minutes)
- Section 2 = your practises (check R notebooks, replicate the results, think about how to run the
analysis)
- Section 3 = tutorial videos (5-10 minutes)
Case discussions: on Wednesdays
- Key methods to link analytics with marketing insights and strategies
- Data-driven (may be very different from general case discussion)
- For quality of case discussions, we split into two sections
- Twice the same contents
- Time:
o Group 1 = 13-14:45
o Group 2 = 15:00-16:45
SECTION 3: Case discussion
“Jetstar” example, background:
- Competing of two cheap airlines → analyse consumer preferences! What kind of factors are
influencing choices for cheap flights
- Opportunities for analytics?
- Marketing goals of analytics?
- Which tools to apply?
In the end: strategy recommendations
- How to formulate strategies based on analytical results?
ASSESSMENT
Sign up in duo’s! → Groups sign up on canvas.
, 2 types of questions
- Analysis & interpretation
- Conceptual or managerial questions
Each 15% → 2 assignments of session 3 and session 6 → 10 days to work on the assignment!
Exam (70%) → offline and two-hours → December 20th
Analytics + questions
- Conceptual questions and interpretation of R output
- Exemplary questions will be posted on BB in due time
CLOSED BOOK EXAM!!!
You get output -> explain and interpret. Little bit calculation (bring calculator!!), some ethics questions,
compare different methods (conceptual). No statistical mathematic included at all!
Exam on paper!! NOT online!
Group 2!! For discussion groups. Group 2 = 15:00-16:45
2 MARKET RESPONSE MODEL
LECTURE 1-11-2021
Structure this week:
- Lecture = Monday
- Tutorials = Tuesday
- Case discussion = Wednesday
SECTION 1: Agenda
1. Linear regression! -> use predictive modelling
2. Making assumptions -> how to do it? And how to check the assumptions? What to do when
assumptions are violated
Video: target knew teen was pregnant before her dad
- Computer model: finding out behaviour in shops which predicted pregnancy. VB. lotion in large
quantities
- Baby ads looked random -> habits matter -> predicting consumer behaviours
SECTION 2: Prediction and linear regression
Description of a prediction machine:
Feed machine with data → put in the machine → get prediction
Objective = to find functional relationship between input (variables) and output (something you want to
predict).
Prediction machines:
