Assignment 2: Market Segmentation & Conjoint Analysis

Assignment Overview

Part I: Segmentation

A. Take a look at the dataset description and at your data. Which of these variables should be seen as numeric? Which should be seen as categorical? Why is it not appropriate to use categorical inputs in a k-means model (even if the values are represented by numbers?)

B. How does this function help you to gain an overall sense of the columns and values in this (or any other) dataset? Why is this valuable for any analyst who will use a dataset to build a model?
a. Does this dataset contain any missing values? If so, how many? Which columns have missing values?
b. What about impossible values? Do you see any impossible values here? If so, handle them in any way that you see fit. Why did you take this approach?

D. Why did you choose this set of 5 variables?
a. Do your variables need to be standardized? Why or why not?
b. If your data requires standardization, use Python to convert your values into z-scores, and store the normalized data in a new dataframe. If not, proceed to the next step without changing the variables.
a. Build an elbow chart to help give you a sense of how you might build your model.
b. How many clusters will you use for your k-means model?

G. Build a k-means model with your desired number of clusters.

H. Generate the centroid values (i.e., the mean values of each variable for each cluster) and display them.

1. Build any four simple visualizations to help management better understand your clusters.

2. For each one of your visualizations, include 2–3 sentences of description/explanation. What does it show about your model?

J. Give a descriptive name to each one of your clusters, along with a few sentences of explanation for the name that you chose.

K. For each cluster, also include a couple sentences about targeting. What types of visitors would be interested in attending the park on the day types you have identified, and how should Lobster Land reach them?

L. How can Lobster Land use this model?

Part II: Conjoint Analysis with a Linear Model

A. Read the dataset night_show.csv into your local environment in Jupyter Notebook or Colab.

B. Based on the descriptions shown above, which of your variables are numeric, and which are categorical?

C. Why should the numeric input variables based on this survey data be dummified?

D. Instead of building a model, we could just rank the bundles by average rating, in descending order, and then just tell Lobster Land to implement all the features in the highest-rated bundle. What would we miss by doing this, though? What value does a conjoint analysis model provide, which we would not have if we simply ranked the bundles?

E. Build a linear model with your data, using the average rating as the outcome variable, and with all of your other variables (other than the bundleID) as inputs.

F. Display the coefficient values of your model inputs.

G. Write two-three paragraphs for Lobster Land management about what your model is showing you.

Part III: Wildcard – Marketing & Segments

A. Find ANY advertisement…ANYWHERE.

B. Write ONE thoughtful paragraph that addresses the issue of segmentation.

• What consumer segment is your ad targeting?
• What makes you think this?
• What types of consumers are in the segment?
• Are you part of the segment?
• Or, alternatively, is your ad an undifferentiated (mass market) ad?
• Finally, what is your opinion of this ad – is it effective?

Assessment Requirements – Brief Summary

This assessment, Assignment 2: Market Segmentation & Conjoint Analysis, was divided into three main parts:

1. Part I – Segmentation (K-means clustering)

   • Importing and exploring dataset ( days25.csv ).

   • Identifying numeric vs. categorical variables.

   • Handling missing or impossible values.

   • Selecting five variables for clustering.

   • Standardizing data and preparing for modeling.

   • Using the elbow method to decide the number of clusters.

   • Building a k-means model and analyzing centroids.

   • Creating four visualizations to interpret clusters.

   • Naming and describing each cluster.

   • Suggesting targeted strategies for each cluster.

   • Discussing how Lobster Land can use the model for operations and marketing.

2. Part II – Conjoint Analysis with a Linear Model

   • Importing and preparing dataset ( night_show.csv ).

   • Identifying numeric vs. categorical variables.

   • Applying dummy variables to inputs.

   • Explaining why a model is better than simple rankings.

   • Building a linear regression model to interpret preferences.

   • Displaying coefficient values for features.

   • Writing managerial insights on customer preferences and trade-offs.

3. Part III – Wildcard: Marketing & Segments

   • Selecting a real-world or online advertisement.

   • Analyzing the segmentation strategy used.

   • Reflecting on the target audience, effectiveness, and relevance.

Academic Mentor’s Step-by-Step Approach

1. Understanding the Dataset & Variables
   The mentor first guided the student to import both datasets into Jupyter Notebook. A discussion was held on differentiating between numeric and categorical variables and why categorical variables are not directly suitable for k-means.

2. Data Cleaning & Preparation
   Next, the mentor explained how to check for missing values and impossible entries. Together, the student applied handling techniques (removal or imputation) and selected five relevant variables for clustering. This was justified based on logical connections to visitor behavior.

3. Standardization & Model Building
   The mentor emphasized why standardization is critical in k-means and demonstrated z-score transformation. An elbow chart was built, and the student experimented with different cluster numbers before finalizing the model.

4. Clustering Interpretation
   The student learned to generate centroids and visualize clusters using scatterplots, bar charts, and histograms. For each visualization, the mentor guided writing short interpretations. Naming clusters and suggesting targeted marketing strategies were also developed through brainstorming.

5. Conjoint Analysis Guidance
   For Part II, the mentor explained dummy variable creation and why even numeric values needed dummification in this context. Instead of ranking bundles, the mentor demonstrated how regression provides insights into individual features. Coefficients were interpreted to highlight customer trade-offs between entertainment types, show length, dining, and crowding levels.

6. Managerial Insights Writing
   The mentor encouraged the student to go beyond numbers, discussing themes such as noise preferences, family vs. adult audiences, and event accessibility. This helped the student practice writing professional recommendations for management.

7. Wildcard Activity – Marketing Reflection
   For Part III, the student analyzed an advertisement by identifying the consumer segment, motivations, and effectiveness. The mentor ensured the reflection linked back to segmentation theory from Part I.

Final Outcome & Learning Objectives Covered

By the end of the assessment, the student successfully:

• Conducted data exploration and cleaning for real datasets.

• Understood numeric vs. categorical data in clustering and regression.

• Applied k-means clustering and interpreted cluster results with meaningful visualizations.

• Practiced data standardization and its importance in modeling.

• Built a linear regression model for conjoint analysis and understood the added value beyond simple ranking.

• Learned to interpret coefficients to derive actionable business insights.

• Reflected on marketing segmentation strategies using real-world advertisements.

This structured approach allowed the student to gain both technical skills (Python, data handling, modeling, visualization) and analytical skills (interpretation, segmentation strategy, managerial recommendations).

Get Expert Guidance for Your Assignment Success

Looking for clarity on how to approach Assignment 2: Market Segmentation & Conjoint Analysis? You can download the sample solution provided here to understand the structure, key concepts, and step-by-step approach used by academic mentors.

Important Note: This sample solution is strictly for reference purposes only. Submitting it as your own work may lead to plagiarism issues and academic penalties. Use it to learn, not to copy.

If you want a unique, plagiarism-free solution tailored to your specific requirements, our team of professional academic writers is ready to help. By ordering a fresh solution, you’ll receive:

• 100% original and plagiarism-free work

• Step-by-step explanations in line with your assessment needs

• Timely delivery before your deadline

• Expert guidance from qualified subject specialists

Take control of your academic journey today use the sample for learning, or order a fully customized solution written just for you.

Choose your next step below:

Download Sample Solution                      Order Fresh Assignment