 |
Analytic Techniques |
|
Bayesian Methods
- Predict the brand a household will choose for a given purchase occasion
Bayesian Networks
- Build integrated models of consumer behavior that can be estimated with limited amounts of data using monte carlo simulations
CHAID
- Identify and differentiate characteristics of best customers from others in the database
Cluster Analysis
- Segment customers into discrete groups based on multiple dimensions
- Group products into bundles based on similarity
- Segment markets and determine target markets
- Develop product positioning and launch new products
- Select test markets
Collaborative Filtering
- Predict items (movies, music, books, news, Web pages) that a user may be interested in, given some information about the user's profile
Conjoint Analysis
- Determine the combination of attributes that would be most satisfying to consumers
Discriminant Analysis
- Predict propensity to respond vs. buy based on prior purchase and promotion history
|
Factor Analysis
- Obtain underlying dimensions from responses to product attributes identified by the researcher
Fuzzy Logic
- Determine baseline sales to enable a more accurate measurement of promotion and advertising effectiveness
Genetic Algorithms
- Optimize the placement and numbers of callouts within a web page layout to grow, on an ongoing basis, a page's marketing gains
Linear Regression
- Predict the dollar value of purchases associated with a mailing
Logistic Regression: Binary
- Predict customers that are most likely to respond to a mailing
Logistic Regression: Multinomial
- Predict customers that are most likely to purchase different products in a catalog mailing
Logit Analysis
- Assess the scope of customer acceptance of a product, particularly a new product. Determine the intensity or magnitude of customers' purchase intentions and translate them into a measure of actual buying behaviour.
Markov Chains
|
Multidimensional Scaling <<
- Obtain underlying dimensions from respondents' judgements about the similarity of products
Neural Networks
- Predict customer demand and segment customers into well-defined categories
Perceptual Mapping
- Display the perceptions of customers or potential customers on attributes such as position of a product, product line, brand, relative to competitors
Preference Regression
- Determine consumers' preferred core benefits. Supplement product positioning techniques like multi dimensional scaling or factor analysis to create ideal vectors on perceptual maps.
Structural Equation Modeling
- Hypothesise models of market behaviour, and test or confirm these models
Survey Design and Analysis
- Collect information on product attributes and/or spending potential on a sample of the customer base
Back to Analytics
|
|
