CHAPTER 3 Research design Data sources 3 1

CHAPTER 3 Research design , Data sources

3 -1 Research Design: Delineating What Data to Collect and How to Collect It A research design is the basic plan that guides data collection and analysis. It must specify: the type of information to be collected (consistent with the project objectives) possible data sources the data collection procedure (accurate, economical and timely)

3 -1 a Types of Research 1. exploratory research – to improve research 2. conclusive research – to help choose between courses of action 3. performancemonitoring research – feedback on chosen course of action Figure 3 -1 Types of research

3 -1 b Exploratory Research: Determining the 'Space' of Possible Marketing Actions Exploratory research facilitates problem recognition and definition. It is appropriate when the research objectives include: � identifying problems or opportunities � gaining perspective on the nature of the problem � gaining perspective on variables involved � establishing priorities � formulating possible courses of action � identifying possible pitfalls in doing conclusive research

3 -1 c Conclusive Research: Narrowing Down Strategic Alternatives Conclusive research aims to narrow the field of strategic alternatives down to one. Two types: �Descriptive research characterizes marketing phenomena without testing for cause-and-effect relationships. It is used for: �determining the frequency of certain marketing phenomena �determining the degree of association between marketing variables �making predictions regarding marketing phenomena �Causal research gathers evidence on cause-and- effect relationships through experimentation.

3 -1 i Longitudinal Design and Panel. Based Research Consumer panels monitor performance continuously for a fixed sample measured repeatedly over time (longitudinally). Advantages of panels: �reveal important aspects of consumer behavior that cannot be gleaned from cross-sectional data �gather more accurate data than cross-sectional surveys �gather extensive background and geodemographic information on participants �reduce bias through period-by-period recording of purchases �tend to cost less per data point than surveys

3 -2 Data Sources for Marketing Research Applications Sources of marketing data: 1. respondents � communication with respondents �verbal response through focus group or in-depth interviews �depends on self-reporting � observation of respondents �accurately records what people do and how �omits reporting of underlying attitudes 2. analogous situations � case histories � simulations

3 -2 Data Sources for Marketing Research Applications (cont. ) Sources of marketing data (cont. ): 3. experimentation to test cause-and-effect relationships �direct manipulation of key independent variables and measurement of their effects on dependent variables �controlling other variables that might affect ability to make valid causal inferences 4. secondary data �data already collected for some other purpose �internal or external

3 -3 Secondary Data � internal secondary data generated within the organization �lower cost �accurate �more available � external secondary data – generated by government or syndicated sources �government publications �trade association data �books �bulletins �reports �periodicals

The Balancing Act with Secondary Data *Inexpensive *Can be Secured Quickly *Unknown Accuracy *Ill Fitting for the Problem

The Nature of Secondary Data Primary data Secondary data Internal Information Sales & Expense reports Salespeople’s reports Street News Executive Judgments Extended internal information

The Nature of Secondary Data (contd. , ) Secondary data External Information Library sources Books Periodicals Government documents Computerized databases Nonlibrary sources Trade associations Government Agencies Media companies Syndicated data Internet sources

Creating an Internal Database An Internal Database is a collection of related information developed from data already within the organization. Why is it important? Case of Capital One Lifetime Value Collective memory banks Created from qualitative data NUD*IST

How a modern database system works Customer Transactions Mail, Email, Phone Marketing Database Inputs from Retail, Phone, Web Updated several times per day Data Access And Analysis Software Appended Data Marketing Staff Access on the web

Two Kinds of Database People Constructors People who build databases Merge/Purge, Hardware, Software Creators People who understand strategy Build loyalty and repeat sales You need both kinds!

Retention is the way to measure loyalty

Retention pays better than acquisition

Building Customer Value in four words. . . Treat different custome rs differentl

What doesn’t work: Treating all customers alike Profit % This 28% lost 22% of the bank’s profits! Bank Customers by Profitability

Compared with newcomers, Long term customers: Buy more per year Buy higher priced options Buy more often Are less price sensitive Are less costly to serve Are more loyal Have a higher lifetime value

Key retention strategy: cross selling

Why do businesses exist at all? Answer: Customers! Get more customers Keep them longer Grow them into bigger customers

Marketing to Customer Segments Your Best Customers 80% of Revenue Your Best Hope for New Gold Customers 1% of Total Revenue GOLD Move Up These may be losers Spend Service Dollars Here Spend Marketing Dollars Here Reactivate or Archive

Examples of Profitable Strategies Newsletters Surveys and Responses Loyalty Programs Customer and Technical Services Friendly, interesting interactive web site Event Driven Communications

Lifetime Value Net profit you will receive from the transactions with a given customer during the time that he/she continues to buy from you. Lifetime value is “Good Will” To compute it, you must be able to track customers from year to year Main use: To evaluate strategy

Long term customers buy more often

Long term customers buy higher priced items

Retention rates go up over time

Model Assumptions There is only one customer segment Acquisition of new customers only happens in year 1 Lapsed customers

Revenue Side of the Equation

Cost Side of the Equation Year 1 Year 2 Year 3

Profit Side of the Equation Gross Profit = Total Revenues – Total Costs Discount Rate = [1+(i * rf)] n where n = no of years to be discounted rf = risk factor Net Present Value (NPV) Profit = Gross Profit / Discount Rate Cumulative Profit = Sum of all NPV Profit till current year Lifetime Value = Cumulative Profit for the year / Total Number of customers ‘N’

Profit Side of the Equation Year 1 Year 2 Year 3

Scoring Customers – RFM Analysis Create a customer database. Include prospects. Use past customer behaviors to predict future behaviors.

Using RFM to find best customers Recency, Frequency, Monetary (RFM) analysis can be used to categorize customers. Best Customers are those who: Bought from you recently Buy from you frequently Spend a lot of money on your products and services.

Recency • Recency is the time that has elapsed since the customer made his most recent purchase. • A customer who made his most recent purchase last month will receive a higher recency score than a customer who made his most recent purchase three years ago. • Example of a Scoring system: • 1 = Customers who made a purchase more than 9 months ago 2 = Customers who made a purchase more than 3 months ago but fewer than 9 months ago 3 = Customers who made a purchase in the last 3 months

Frequency is the total number of purchases that a customer has made within a designated period of time. A customer who made six purchases in the last three years would receive a higher frequency score than a customer who made one purchase in the last three years. Example of a Scoring system: 1 = Customers who made a single purchase in the past 12 months 2 = Customers who made between two & 12 purchases in the past year. 3 = Customers who made more than 12 purchases in the past year.

Monetary is each customer's average purchase amount. A customer who averages a $100 purchase amount would receive a higher monetary score than a customer who averages a $20 purchase amount. Example of a Scoring system: 1 = Customers with an average purchase amount up to $15. 2 = Customers with an average purchase amount from $15 to $50. 3 = Customers with an average purchase amount greater than $50.

Calculating RFM Rank customers in your databased on time since last purchase - Divide into 3 equal groups with 3 being the 33% of customers who bought most recently Do the same thing again for Frequency. Repeat the same exercise for Monetary or total dollars spent. These three codes give us 27 different categories of customers ranging from 333 – 111.

ANALYZE your Customers: Highest Monetary Cells 113 213 313 123 223 323 133 233 333

ANALYZE your Customers: Lowest Monetary Cells 111 211 311 121 221 321 131 231 331

Benefits of RFM Analysis • RFM Analysis can provide answers to the following • • • questions: Can I identify my best customers? Who do I e-mail offers to? When do I e-mail them? How often? Should I promote to some customers more often than others? How can I tell when I’m losing a customer? Can I refine my marketing mix variables? The next step after knowing and analyzing your customers is CLONING your customers.

Advantages of Secondary Data Clarify or redefine the problem /opportunity May actually provide solutions May provide primary research method alternatives May divulge potential difficulties May provide necessary background information

Limitations of Secondary Data Lack of availability Lack of relevance Resources

Appraising Secondary Data Who sponsored the research? Who conducted the research? Who provided the information? Who reported the information? What information was gathered? Why was the information gathered? When was the information gathered? How was the information gathered? Where was the information gathered?

A Decision Support System What is a DSS? An interactive, personalized mapping system designed to be initiated and controlled by decision makers In Marketing, it is known as MKIS (Marketing Information Systems) Some basic ideas about MKIS Complex systems Deal with a variety of data sources Cost-benefit considerations

Characteristics of an MKIS Interactive Flexible Discovery oriented Easy to learn and use

Advantages of an MKIS Cost savings Increased understanding of the decision environment Better decisions Improved value of the information

Data Mining What is Data Mining? the process of exploration and analysis, by automatic and semiautomatic mean, of large quantities of data in order to discover meaningful patterns and rules. The technology is "data mining. " Extension of statistics.

Data Mining Primarily used by companies with a strong ‘customer’ focus Wal Mart NBA Advanced Scout

Data Mining Customer Acquisition Customer retention or loyalty Customer abandonment Market-basket analysis