Escolar Documentos
Profissional Documentos
Cultura Documentos
0
0
0
u
n
i
t
s
M
e
d
i
a
s
p
e
n
d
,
0
0
0
U
S
D
2%
4%
6%
8%
10%
12%
14%
Total Spends Magazine TV Daily
Evaluate Efficiency/ROI from each media vehicle
E
f
f
i
c
i
e
n
c
y
0
100
200
300
400
500
600
700
800
900
0
2
4
6
8
10
12
14
16
18
20
Baseline sales Online incr. sales TV incr. sales Daily incr. sales
Online spend TV spend Dailies spend
Decomposed sales into base line and incremental
Market Mix Modeling
Marketing budgets as a percentage of sales typically vary between 4-10% for a CPG company. Given the high
investment, marketers would like to evaluate the returns from each media vehicle and optimize their
investments.
Market Mix Modeling (MMM) helps brand managers identify the right mix of advertising media, manage
channels and allocate marketing spend in a manner that not only provides the required sales lift but also
maximizes the returns on investment by media vehicles.
The model captures the following:
Cannibalization, if any, amongst the portfolio of brands
Impact of competition media activity
Saturation spends for each media vehicle based on diminishing returns
Decay impact, if any for each of the media vehicles - also called ad-stock
Knowledgeable
2%
Quality Conscious
4%
Soft Shiny Hair
4%
Better Color
Experience 1%
Natural
Ingredients 2%
Pleasant
Fragrance 1%
Gray coverage
1%
Value for Money
0.4%
Feel young In
charge 15%
Sensuous &
Sophisticated 14%
Perfect color
13%
Recommended
brand 11%
Brand that keeps
its promises 9%
Range of Shades
8%
Makes me feel
confident 9%
Intense, long
lasting colors 5%
Purchase Intent
Colour pathway Non-damaging pathway Experiential
Emotional response
Rational response
Brand image
Brand attributes
Market
Performance
Driver Analysis
Every organization needs to understand which product/service attributes have the greatest influence on the
consumers purchase decision. For instance, consumers might rate a personal care product based on its color,
scent, functionality, price, discount offer and so on. Driver analysis is a technique widely used to identify the
key consumer needs which translates to purchase behavior. It provides answers to critical questions like:
What accounts for consumers proclivity to purchase the product?
What causes consumers to switch to competitor brands?
What is the core consumer segment that should be focused on?
Statistical techniques (Correlation, Multivariate Regression, and Structural Equation Modeling) are utilized to
identify the critical success factors of a brand which drives sales or revenue.
Identify growth opportunities for niche
consumer segments
Define the portfolio strategy for their
category by ensuring minimal consumer
segment overlap across brands
Based on the above, the marketing team
modifies their product/service offering and
deploys the desired positioning and
marketing communication to reach their
consumer base.
Healthy hair
Seekers
Natural
enhancers
Expressive
Age defiers
Young subtle
expressers
Young strong
expressers
Original color
of hair
without hair
colorant
Color of hair
with hair
colorant
(Aspired
Color)
Dark Brown
Medium Brown
Light Brown
Medium Brown
Medium Blonde
Dark Blonde
Light Brown
Dark Brown
Medium Brown
Medium Brown
Dark Blonde
Medium Blonde
Light Brown
Medium Brown
Medium Blonde
Dark Brown
Chestnut
Medium Blonde
Auburn
Dark Brown
Auburn
Auburn
Chestnut
Auburn
Chestnut
Market
Performance
Consumer Segmentation
Segmentation identifies homogenous consumer groups based on their needs, preferences, attitudes,
demographics, lifestyle measures (activities, interests, opinions and values) and behavior.
A mass marketing approach treats the market as a whole, while segmentation enables the business to target
different consumer groups by adapting its product and marketing mix to suit each targeted segment.
Segmentation results are leveraged to:
Understand how the market is evolving in terms of changing consumer needs/preferences
Identify the benefits sought by each consumer segment
Improve the competitive position by focusing on the most profitable and sizeable segment
Assessing brand value helps in:
Identifying optimal measures to build
strong brand equity
Demonstrating the effect of strong
brand equity in terms of market share,
consumer acquisition, brand loyalty and
other desirable outcomes
Mapping the brand's equity against that
of key competitors
Judgments
Resonance
Feelings
Imagery Performance
Salience
Stages of brand development
4. Relationships =
What about you and me?
3. Response=
What about you?
2. Meaning=
What are you?
1. Identity=
Who are you?
Branding objective at each
stage
Intense, Active
loyalty
Positive, Accessible
reactions
Points-of-parity
& Difference
Deep, Broad
brand awareness
Kellers Brand Resonance Pyramid
Market
Performance
Brand Equity Tracker
Brand equity tracker provides a framework for measuring the brands performance/health. This can be
assessed through consumer perception, which includes both rational and emotional aspects. Main criteria
for assessment brand differentiation, brand relevance, the consumers knowledge of the brand and brand
image in the consumers mind.
Brand equity tracker defines the gap between what a brand wants to be and how a brand is actually
perceived by consumers, thereby giving a direction for branding strategy. Different components of brand
equity are depicted in the image.
Business Situation:
Clients 70% to 80% of daily beverage production depends on empty bottle returns from previous day. As such, a highly accurate forecast
for daily bottle returns across all SKUs was required for optimal production planning.
The Task:
Design, develop and implement a predictive model that will help in forecasting daily empty bottle returns for 10 different SKUs.
Analytical Framework:
Data preparation for model building. Past sales data or production data didn't have much effect on the returns data and thus past 2 years
return data was used for the model building. Different models like ARIMA, Holt Winters, Year on Year growth model were built to forecast the
returns.
The Result:
For all the SKUs considered, an accuracy of 75% was achieved for May-June 2011. This was significantly better than existing forecasts.
For the SKU which contributed to 47% of the total returns, an accuracy of 92% was achieved for May-June 2011. The monthly accuracy for
May2011 being 85% and June 2011 being 97%.
Analytics in Action
Towards Better Production Planning by Accurate Forecasting
Client: A Leading Carbonated Beverage Manufacturer
Defining
Modelling
universe
Model
development
Validation
Past 2 years empty bottle returns data was
considered. The data was too volatile to fit
into the model and thus Centralized
Moving Averages was calculated to
smoothen the data and to get a better
model fit.
ARIMA model was built on Centralised
moving averages , Holt winters and Year on
Year growth rate models was built on
empty bottle returns. Bootstrapping
method was applied to choose best
forecast value.
May and June forecasts were compared
against actuals. Accuracy was calculated at
a daily-level for all SKUs
-
5,000
10,000
15,000
20,000
25,000
30,000
5
/
1
/
2
0
0
9
5
/
2
3
/
2
0
0
9
6
/
1
4
/
2
0
0
9
7
/
6
/
2
0
0
9
7
/
2
8
/
2
0
0
9
8
/
1
9
/
2
0
0
9
9
/
1
0
/
2
0
0
9
1
0
/
2
/
2
0
0
9
1
0
/
2
4
/
2
0
0
9
1
1
/
1
5
/
2
0
0
9
1
2
/
7
/
2
0
0
9
1
2
/
2
9
/
2
0
0
9
1
/
2
0
/
2
0
1
0
2
/
1
1
/
2
0
1
0
3
/
5
/
2
0
1
0
3
/
2
7
/
2
0
1
0
4
/
1
8
/
2
0
1
0
5
/
1
0
/
2
0
1
0
6
/
1
/
2
0
1
0
6
/
2
3
/
2
0
1
0
7
/
1
5
/
2
0
1
0
8
/
6
/
2
0
1
0
8
/
2
8
/
2
0
1
0
9
/
1
9
/
2
0
1
0
1
0
/
1
1
/
2
0
1
0
1
1
/
2
/
2
0
1
0
1
1
/
2
4
/
2
0
1
0
1
2
/
1
6
/
2
0
1
0
1
/
7
/
2
0
1
1
1
/
2
9
/
2
0
1
1
2
/
2
0
/
2
0
1
1
3
/
1
4
/
2
0
1
1
4
/
5
/
2
0
1
1
4
/
2
7
/
2
0
1
1
5
/
1
9
/
2
0
1
1
6
/
1
0
/
2
0
1
1
2009
D
a
i
l
y
r
e
t
u
r
n
s
Actuals
Forecasts
Model Build on 2009 and 2010 data Model Application for May-June11
2009 2010 2011
-
5,000
10,000
15,000
20,000
25,000
30,000
35,000
1
-
M
a
y
-
1
1
3
-
M
a
y
-
1
1
5
-
M
a
y
-
1
1
7
-
M
a
y
-
1
1
9
-
M
a
y
-
1
1
1
1
-
M
a
y
-
1
1
1
3
-
M
a
y
-
1
1
1
5
-
M
a
y
-
1
1
1
7
-
M
a
y
-
1
1
1
9
-
M
a
y
-
1
1
2
1
-
M
a
y
-
1
1
2
3
-
M
a
y
-
1
1
2
5
-
M
a
y
-
1
1
2
7
-
M
a
y
-
1
1
2
9
-
M
a
y
-
1
1
3
1
-
M
a
y
-
1
1
2
-
J
u
n
-
1
1
4
-
J
u
n
-
1
1
6
-
J
u
n
-
1
1
8
-
J
u
n
-
1
1
1
0
-
J
u
n
-
1
1
1
2
-
J
u
n
-
1
1
1
4
-
J
u
n
-
1
1
1
6
-
J
u
n
-
1
1
1
8
-
J
u
n
-
1
1
2
0
-
J
u
n
-
1
1
2
2
-
J
u
n
-
1
1
2
4
-
J
u
n
-
1
1
2
6
-
J
u
n
-
1
1
2
8
-
J
u
n
-
1
1
3
0
-
J
u
n
-
1
1
D
a
i
l
y
R
e
t
u
r
n
s
Actuals
Forecast
Business Situation:
The client, a leading hair care manufacturer wanted to identify drivers of brand preference for the category which would aid them in designing
the right marketing strategy & related collateral for strengthening market share for their existing brand.
Analytical Framework:
Design a Structural Equation Model (SEM) to identify key equity themes & their hierarchy in terms of importance in driving purchase for the
category, and identify the best pathway to improve the brands equity in consumers mind.
The Result:
The following recommendations were made and implemented by the business:
Leverage Brands strength on the health dimension this goes in line with brands equity pyramid
Ingredient is one of the key category drivers on which the brand is performing very well strengthen communication strategy to
capture this
Even though health benefit is key, consumers eventually desire the beauty aspect Redesign communication strategy to convey this
as the end benefit
Currently beauty dimension is weak build credibility on that with consistent communication
Analytics in Action
Re-design Product Communication Strategies in line with Consumer
Preferences
Client: Leading Hair Care Manufacturer
Marketing strategy on the core Health benefit & its eventual impact on making oneself attractive is the Key
Overall Brand Equity
Feel Confident
& Energised
15%
Trust
10%
Effective
8%
Expert Brand
3%
Leaves hair
soft ,smooth
and shiny
11%
Hair Health
10%
Color
Protection
1%
Conditioning
3%
Ingredients
11%
Brand for me
6%
Attractiveness
10%
Beautiful and
Empowered
1%
Leading Brand
2%
Fragrance
5%
Experience
1%
For men and
women
0.3%
Dandruff and
Scalp issues
4%
0.60
0.37
0.83
0.21
0.90
0.63
0.30
0.09
0.29
0.15
0.80
Strong relationship
Moderately strong relationship
Weak relationship
0.78 0.19
0.90 0.90 0.90
0.90
0.90
0.16
Business Situation:
Leading manufacturer in anti-aging cream category. Brand X occupies a dominant position in market; recently also introduced Brand Y.
Brand X Volumes are down 6.5% vs. last year.
Spending across Media has shifted from being TV-centric in 2007 to Dailies-centric in 2008.
Manufacturer would like to understand the effectiveness and efficiency of his Media Spend; and to find optimal ways to reallocate media
spend across channels so as to maintain Sales
The Task:
Need to develop an optimal media investment strategy based on Media Mix Modeling to improve the brand equity of the client :
Establish key relationships between Sales and Marketing driver inputs.
Quantify impact of each marketing driver on sales.
Optimize allocation spends across various drivers to maximize sales.
The Result:
The model gave clear directions for allocating budgets across various media :
For every $ spend, Magazine gives 6 times the return of TV and dailies.
Magazines seems to be operating above threshold and below saturation levels.
Lower returns on TV could be due to operating levels below threshold in certain bursts, and low SOVs compared to Brand Z.
TV has a bigger role of driving the brand health.
Recommendations used to optimize marketing spends across channels to maximize Sales.
Analytics in Action
Increasing ROI by Optimizing Media Spends
Client: A Leading Beauty Products Manufacturer
0
100
200
300
400
500
600
700
800
900
0
2
4
6
8
10
12
14
16
18
20
J
A
N
0
7
F
E
B
0
7
M
A
R
0
7
A
P
R
0
7
M
A
Y
0
7
J
U
N
0
7
J
U
L
0
7
A
U
G
0
7
S
E
P
0
7
O
C
T
0
7
N
O
V
0
7
D
E
C
0
7
J
A
N
0
8
F
E
B
0
8
M
A
R
0
8
A
P
R
0
8
M
A
Y
0
8
J
U
N
0
8
J
U
L
0
8
A
U
G
0
8
S
E
P
0
8
O
C
T
0
8
N
O
V
0
8
D
E
C
0
8
Baseline Sales Magazine Incr. Sales TV Incr. Sales Daily Incr. Sales
test Magazine Spend TV Spend Dailies Spend
V
o
l
u
m
e
,
0
0
0
u
n
i
t
s
M
e
d
i
a
S
p
e
n
d
,
0
0
0
S
G
D
-
0.02
0.04
0.06
0.08
0.10
0.12
0.14
Total Spends Magazine TV Daily
E
f
f
i
c
i
e
n
c
y
Incremental Sales per 000 SGD media spend
Business Situation :
Over-the-Counter (OTC) market is a growing industry; consumers today are much more inclined to self-diagnosis and self-medication as they
prefer to have a greater role in their health affairs. And brand shares are impacted because of multiple influencers like FDA regulations,
mergers and acquisitions, patent expiry, Rx to OTC switch, entry of generics, etc.
The Task :
In this dynamically changing OTC market; there is a need to track OTC industry movement by category and evaluate market share changes
across key geographies /countries . This will enable a business to focus its marketing efforts on areas with the greatest return on investment.
Analysis :
Collated historic (2005-2010) as well as forecasted sales (2011-2015) information.
Accounted for all industry mergers & acquisitions at company X brand X country level
Evaluated category and brand performance at each of the levels defined below:
The Result :
Insights from this analysis helped identify the focus markets and brands by each category. Based on this the client drafted their annual
strategic plan
Analytics in Action
Tracking Market Development in the OTC industry
Client : A Leading Global Manufacturer of Over-the-counter Drugs
Category
1. Cough & Cold
2. Analgesics
3. Vitamins & Minerals
4. Digestive Healthetc.
Geography
1. APAC
2. LA
3. NA
4. WE & EEetc.
Country
1. USA
2. Canada
3. Brazil
4. Chinaetc.
Company
1. J&J
2. GSK
3. Merck
4. Reckitt Benckiseretc.
Brands
(as an example brands
within Analgesics)
1. Tylenol
2. Aspirin
3. Adviletc.
MANAGEMENT TEAM
GLOBAL EXPERIENCE.
PROVEN RESULTS.
Roy K. Cherian
CEO
Roy has over 20 years of rich experience in marketing, advertising and media
in organizations like Nestle India, United Breweries, FCB and Feedback
Ventures. He holds an MBA from IIM Ahmedabad.
Anunay Gupta, PhD
COO & Head of Analytics
Anunay has over 15 years of experience, with a significant portion focused
on Analytics in Consumer Finance. In his last assignment at Citigroup, he was
responsible for all Decision Management functions for the US Cards
portfolio of Citigroup, covering approx $150B in assets. Anunay holds an
MBA in Finance from NYU Stern School of Business.
Kakul Paul
Business Head, CPG & Retail
Kakul has over 8 years of experience within the CPG industry. She was
previously part of the Analytics practice as WNS, leading analytic initiatives
for top Fortune 50 clients globally. She has extensive experience in what
drives Consumer purchase behavior, market mix modeling, pricing &
promotion analytics, etc. Kakul has an MBA from IIM Ahmedabad.
ADVANCED ANALYTICAL SOLUTIONS
MARKETELLIGENT, INC.
80 Broad Street, 5th Floor, New York, NY 10004
1.212.837.7827 (o) 1.208.439.5551 (fax) info@marketelligent.com
CONTACT
www.marketelligent.com
Industry Business Focus Tools and Techniques
Consumer Finance Investment Optimization SAS, SPSS, R, VBA
Credit Cards Revenue Maximization Cluster analysis
Loans and Mortgages Cost and Process Efficiencies Factor analysis
Retail Banking & Insurance Forecasting Structural Equation Modeling
Wealth Management Predictive Modeling Conjoint analysis
Consumer Goods and Retail Risk Management Perceptual maps
CPG & Retail Pricing Optimization Neural Networks
Consumer Durables Customer Segmentation Chaid / CART
Manufacturing and Supply Chain Drivers Analysis Genetic Algorithms
High Tech OEMs Supply Chain Management Support Vector Machines
Automotive Sentiment Analysis
Logistics & Distribution
YOUR PARTNER FOR
DATA ANALYTI CS SERVI CES
Greg Ferdinand
EVP, Business Development
Greg has over 20 years of experience in global marketing, strategic planning,
business development and analytics at Dell, Capital One and AT&T. He has
successfully developed and embedded analytic-driven programs into a
variety of go-to-market, customer and operational functions. Greg holds an
MBA from NYU Stern School of Business