1. Ethnography Vs Datamining ?
(sebuah pendekatan dalam market research)
Suhermin Ari Pujiati
Dayaolahawarta - 2009
ETHNOGRAPHY?
Research method based on immersion
into the daily routines of a particular
user community (in homes offices,
community. homes, offices
shops, hospitals, entertainments spaces,
hospitality, etc.)
Long term, often over several months,
where data is captured through interview
notes, transcribed conversations, film,
videography, d
id h drawings, etc.
i t
Companies use it to gain insights into
the culture and behavior of their
customers.
3. Time and again we see institutional blindness,
compounded by dangerously misleading survey
results. Consumers change their minds,
faster than market research can predict
them……!
“If experience is embedded in the ‘individual’
and if we cannot quantify the individual, how
does ethnography connect the individual to
the collective domain to arrive at any
meaningful generalization?”
4. Trends in Marketing Research
Characteristics of Good Marketing Research
1. Scientific Effective marketing research uses the principles of the
method scientific method: careful observation, formulation of
hypotheses, prediction, and testing.
2. Research At its best, marketing research develops innovative
creativity ways to solve a problem
3. Multiple Marketing researchers shy away from overreliance on
methods any one method. They also recognize the value of
using two or three methods to increase confidence in
the results.
See text for complete table
5. Trends in Marketing Research
Environmental Scanning and
Forecasting
Increased Market Intelligence
Global MISs (I.e.JIGSAW Project)
Data Fusion, Data Mining, Neuro-
biographic
Clustering and Beyond….
Use of Live Data
External research Associates (ERAs)
Deontology Issues
Marketing Intelligence System
A set of procedures and
p
sources used by
managers to obtain
everyday
information about
developments in
the
th marketing
k ti
environment.
6. Database Marketing
Database marketing companies have already
made significant progress integrating public
sources of customer data ( including census
f t d t i l di
data, birth records, bankruptcy and divorce
proceedings, real-estate transactions, motor
vehicle registrations, and driver’s license
information) with private data sources (such as
point-of-sale data, credit/debit card and ATM
transactions,
transactions telephone billing information,
information
membership lists, home shopping activities,
electronic ticketing, etc.).
DATAMINING ?
Data mining is a new discipline lying at the interface
of statistics, database technology, pattern
f t ti ti d t b t h l tt
recognition, machine learning, and other areas.
It is concerned with the secondary analysis of large
databases in order to find previously unsuspected
relationships which are of interest or value to
the database owners.
(David J. HAND)
7. DATAMINING ?
Data mining tools are now being developed to
sift through the marketing data to identify
patterns and relationships using traditional
analytic tools like regression, cluster analysis, and
decision trees, and newer technologies like
Artificial Neural Networks, Genetic Algorithms,
and Bayesian Networks.
New Market Research System
N M k tR hS t
Ethnography & Datamining
8. Marketing Research System
The Marketing Research Process
Step 1: Define the Problem, the Decision
Alternatives, and the Research Objectives
Step 2: Develop the Research Plan
Data Sources
Research Approaches
Observational research
Focus group research
Survey research
S h
Behavioural data
Experimental research
Ethnography
Marketing Research System
Research Instruments
Questionnaires
Psychological tools
Mechanical devices
Quantitative measures
Sampling Plan
Sampling unit
Sample size
Sampling procedure
9. Probability and Nonprobability Samples
A. Probability Sample
Simple random sample Every member of the population has an
equal chance of selection
Stratified random sample The population is divided into mutually
exclusive groups (such as age groups),
and random samples are drawn from
each group
Cluster (area) sample The population is divided into mutually
exclusive groups (such as city blocks),
blocks)
and the researcher draws a sample of the
groups to interview
Continued on next slide . . .
Probability and Nonprobability Samples (Continued)
A. Nonprobability
Sample
Convenience sample The researcher selects the most
accessible population members
Judgment sample The researcher selects population
members who are good prospects for
accurate information
Quota sample The researcher finds and interviews a
prescribed number of people in each of
several categories
10. Marketing Research System
Step 3: Collect the Information
Step 4: Analyze the Information
Step 5: Present the Findings
Step 6: Make the Decision
Forecasting and
Demand Measurement
Forecasting and Demand Measurement
The Measures of Market Demand
Which Market to
Ma ket
Measure?
Market
Potential market
Available market
Target market
g
(severed market)
Penetrated market
11. Forecasting and Demand Measurement
A Vocabulary for Demand Measurement
Market Demand
Market share
Market penetration index
Share penetration index
Market Forecast
Market Potential
Product penetration percentage
Company Demand
Company Sales
Forecast
Sales quota
Sales budget
Company Sales Potential
Forecasting and Demand Measurement
Estimating Current demand
Total Market Potential
Area Market Potential
Market-Buildup Method
Multiple-Factor Index Method
Brand development index (BDI)
Industry Sales and Market Shares
Estimating Future Demand
Survey of Buyers’ Intentions
Forecasting
Purchase probability scale
12. Research is the art of seeing what everyone else
has seen, and doing what no-one else has
done…..!
done !
….metrics are learned men’s Excuses…..!
…don’t fear change, embrace it…….!
…..if we knew what we were doing, it wouldn t be
if doing wouldn’t
research………!
