Scribd Logo
Upload

Welcome to Scribd!

  • 8 views

    Stats

    Uploaded by

    abhishek.baidya
    The document describes several machine learning and statistical techniques including multiple regression, discriminant analysis, cluster analysis, multidimensional analysis, and conjoint analysis. It provides definitions of the techniques, their classification as supervised or unsupervised learning, common algorithm types, measures used, applications, and examples.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd

    Stats

    Uploaded by

    abhishek.baidya
    8 views2 pages
    The document describes several machine learning and statistical techniques including multiple regression, discriminant analysis, cluster analysis, multidimensional analysis, and conjoint analysis. It provides definitions of the techniques, their classification as supervised or unsupervised learning, common algorithm types, measures used, applications, and examples.

    Copyright

    © © All Rights Reserved

    Available Formats

    PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    The document describes several machine learning and statistical techniques including multiple regression, discriminant analysis, cluster analysis, multidimensional analysis, and conjoint analysis. It provides definitions of the techniques, their classification as supervised or unsupervised learning, common algorithm types, measures used, applications, and examples.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    8 views2 pages

    Stats

    Uploaded by

    abhishek.baidya
    The document describes several machine learning and statistical techniques including multiple regression, discriminant analysis, cluster analysis, multidimensional analysis, and conjoint analysis. It provides definitions of the techniques, their classification as supervised or unsupervised learning, common algorithm types, measures used, applications, and examples.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    of 2

    Method Definition Classification Types

    - Simple Linear Regression: One


    independent variable. - Multiple
    Predicts a dependent variable based on Linear Regression: Multiple
    Multiple Regression multiple independent variables. Supervised Learning independent variables.

    - Linear Discriminant Analysis (LDA):


    Linear combinations of predictors. -
    Classifies observations into predefined Quadratic Discriminant Analysis
    Discriminant Analysis groups based on independent variables. Supervised Learning (QDA): Non-linear boundaries.

    - Hierarchical Clustering: Builds a


    tree-like structure of clusters. - K-
    Groups similar observations into clusters Means Clustering: Divides data into
    Cluster Analysis based on their characteristics. Unsupervised Learning K clusters.

    - Principal Component Analysis


    (PCA): Reduces dimensionality. -
    Examines relationships among multiple Factor Analysis: Identifies latent
    Multidimensional Analysis variables in a multi-dimensional space. Unsupervised Learning factors.

    - Choice-Based Conjoint (CBC):


    Assesses consumer preferences by Respondents choose preferred
    analyzing trade-offs among product options. - Profile-Based Conjoint:
    Conjoint Analysis attributes. Market Research Technique Ranking or rating profiles.
    Measures Application Examples

    - Coefficient of Determination (R- - Sales Forecasting: Predicting sales based - Predicting house prices based on square footage,
    squared): Explains variance. - on advertising spend, seasonality, etc. - location, and number of bedrooms. - Estimating
    Regression Coefficients: Impact of Economic Modeling: Predicting GDP crop yield based on rainfall, temperature, and soil
    predictors. growth based on various factors. nutrients.

    - Discriminant Function Coefficients: - Credit Scoring: Determining - Categorizing customers into high, medium, or
    Influence of predictors. - Wilks’ Lambda: creditworthiness. - Medical Diagnosis: low risk for loan approval. - Diagnosing diseases
    Overall significance. Identifying disease categories. based on patient symptoms.

    - Silhouette Score: Cluster quality. - - Market Segmentation: Identifying - Segmenting customers based on purchasing
    Centroid Distances: Measure of customer segments. - Image behavior. - Identifying distinct regions in satellite
    similarity. Segmentation: Grouping pixels in images. images.

    - Eigenvalues and Eigenvectors: - Marketing Research: Understanding - Reducing features in a dataset while preserving
    Variance explained. - Factor Loadings: consumer preferences. - Social Sciences: variance. - Identifying underlying factors
    Strength of associations. Studying interrelationships. influencing survey responses.

    - Part-Worth Utilities: Attribute - Product Design: Optimizing features. - - Determining optimal smartphone features based
    importance. - Importance Scores: Pricing Strategies: Understanding trade- on user preferences. - Pricing a subscription
    Relative impact. offs. service considering different plan features.

    You might also like