Group work

TODO: VALIDATE

In this group project, you will develop and analyze a realistic business analytics case, including data, modeling, and critical reflection. The project focuses on business-relevant contexts such as management, finance, operations, or digital platforms. You will design and work with a synthetic dataset that reflects a realistic organizational process or decision situation. This allows you to address both upstream challenges—problem framing and data design—and downstream challenges such as deployment, implementation, ethics, and risk. Your work should be grounded in appropriate and reputable references, such as academic literature and industry reports.

Objectives

  • Design a realistic business analytics scenario
  • Select and apply appropriate analytical models
  • Communicate results using CRISP-DM as a structuring framework
  • Critically reflect on assumptions, limitations, and improvements

Group formation and project allocation

  • The group size is 2–3 participants.

  • Projects may be allocated to more than one group.

  • You may apply individually or as a group.

  • Apply by email and indicate three project preferences, ranked as:

    • Preference 1
    • Preference 2
    • Preference 3

  • For a group application, one email containing the names of all group members is sufficient.

  • Based on the applications, groups will be arranged and projects assigned.

  • If one participant remains after group formation, an existing group may be expanded by one participant.

Project topics

Select a business topic and formulate a concrete analytical question. Suitable domains include:

  • Finance, such as credit default, fraud, or customer lifetime value
  • Marketing, such as churn, customer segmentation, or campaign effectiveness
  • Human Resources, such as attrition, promotion, or team productivity
  • Digital business, such as user engagement, gig worker retention, or pricing strategy

Your project preference should identify a concrete business problem rather than only a general domain.

Task

  • Select a business topic and formulate a concrete question.

  • Create a synthetic but realistic dataset representing internal organizational data. You may complement this with synthetic or real external data if appropriate.

  • Develop an analytical notebook following the CRISP-DM process:

    1. Business understanding
      What is the context, the concrete question, and the decision relevance? Who are the stakeholders?

    2. Data understanding
      What does the dataset contain? How does it reflect a realistic business setting? What insights emerge from exploratory data analysis?

    3. Data preparation
      How is the data cleaned, transformed, and enriched?

    4. Modeling
      Which model is used and why? How is it trained and tuned?

    5. Evaluation
      Which metrics are used? How should the results be interpreted in practice?

    6. Deployment
      How would the model be implemented? What are the requirements, risks, and ethical considerations?

  • Develop a report that presents and critically reflects on the case, including:

    • What can be learned from the case
    • How it connects to or extends course content
    • Simplifying assumptions and limitations
    • Opportunities for improvement
NoteNotes
  • Support key elements of your analysis with reputable sources, particularly the relevance of the problem, typical data sources, and common modeling approaches.
  • Simplifications are acceptable if they are clearly stated and justified.
  • Advanced extensions may include advanced data preparation, model comparison or refinement, robustness checks, interactive visualizations, or more detailed deployment considerations.
  • Your code must run and reproduce your results.
  • If you plan to work with a large-scale big-data scenario, consult with me in advance.
  • Real-time or streaming-data projects are strongly discouraged because they are difficult to implement and evaluate within the scope of this project.

Project process

Application and allocation

Submit your three ranked project preferences by TODO. Groups and projects will then be assigned based on the submitted preferences.

Project work

Develop the case, dataset, analysis, and presentation iteratively. Your work should progress from problem framing and dataset design to analysis, modeling, evaluation, and reflection.

Presentation

  • Presentation date: 2026-10-02
  • Each group has 30 minutes to present the project.
  • Up to 15 additional minutes may be used for questions and discussion.
  • Every group member must present part of the project and contribute to the discussion.
  • Attendance is required for all project presentations.
  • Submit the presentation file and the corresponding analysis files by the presentation deadline.

Final submission

  • Final report deadline: TODO
  • Submit the final text document via the Canvas assignment.
  • Submit the report as a PDF, not as a Word document.
  • The analytical notebook must be executed before submission.

Deliverables

Synthetic dataset generation script

A Python script that:

  • Clearly documents the business context and purpose in the module docstring
  • Defines the data schema and variables
  • Implements data generation logic, including distributions and relationships
  • Includes realism features, such as noise, missing values, or duplicates where appropriate
  • States key assumptions and provides justification where possible
  • Produces reproducible output using a fixed random seed
  • Exports the generated dataset

Dataset

  • CSV file or files containing the simulated data

Analytical notebook

A Jupyter Notebook that:

  • Covers the full CRISP-DM process
  • Includes explanations in Markdown
  • Is fully executable and reproducible

Presentation

A slide deck that:

  • Clearly introduces the business problem and decision context
  • Explains the analytical approach and key modeling decisions
  • Communicates the most important findings and their practical relevance
  • Critically discusses limitations, risks, and potential improvements

Report

Maximum length: 15 pages, including title page and references.

Section 1: Case package

  • Business context and motivation
  • Problem statement and objectives
  • Stakeholders and decision relevance
  • Positioning in practice, supported by references

Section 2: Analytical approach and key findings

  • Overview and justification of the analytical approach
  • Selected key results without duplicating the notebook
  • Key business insights

Section 3: Reflection

  • Assumptions
  • Limitations of the dataset and analytical approach
  • Ethical and deployment considerations
  • Potential improvements and extensions

Evaluation

The group project is an ongoing assessment worth 120 performance points. The evaluation is based on the submitted materials, the presentation, and the discussion.

Each group receives a group evaluation. For the final evaluation of individual participants, supplements or deductions from the group grade may be made based on the individual’s contribution to the project, presentation, and discussion. You are therefore expected to contribute equally and to document your individual contributions clearly and transparently.

Category Points Criteria
A. Case and dataset design 30 pts Clarity and relevance of the problem; realism of the dataset; transparency of data generation
B. Analysis quality 40 pts Method justification; correctness; CRISP-DM use; insightfulness
C. Communication 40 pts Structure; visualization; clean code; argument quality; use of references; reflection; presentation and discussion
D. Advanced extension 10 pts Meaningful additional feature beyond the core requirements

Note: The applied methodology and reasoning are more important than achieving the highest possible model performance.

AI policy

  • Allowed: generating dataset scripts, debugging code, and documentation support
  • Not allowed: generating complete end-to-end solutions
  • You must be able to explain and defend your work at any time
  • All outputs must be validated

Consultation and support

Submission

Submit all required files via the Canvas assignment.

NoteNote

High-quality project work may contribute to future course development, for example by extending teaching materials or informing teaching cases. In such cases, we will discuss how contributions are acknowledged.

Example: Synthetic data generation script

"""
Purpose:
- Simulate [business scenario]

Data schema:
- age: numeric (years)
- income: numeric (annual income in EUR)

Generation logic:
- Age is drawn from a normal distribution (mean=40, sd=10)
- Income depends linearly on age with added noise

Assumptions and justification:
- Age distribution approximates working population demographics
- Income increases with age due to experience (human capital theory)
- Noise reflects unobserved heterogeneity in earnings

References (if applicable):
- [Add source, e.g., industry report or academic literature]
"""

import numpy as np
import pandas as pd

np.random.seed(42)  # Reproducibility

# 1. Define dataset size
n = 1000

# 2. Generate base variables
age = np.random.normal(loc=40, scale=10, size=n)

# 3. Define relationships
income = age * 1000 + np.random.normal(loc=0, scale=5000, size=n)

# 4. Add realism, such as missing values
missing_mask = np.random.rand(n) < 0.05
income[missing_mask] = np.nan

# 5. Create dataframe and export
df = pd.DataFrame({
    "age": age,
    "income": income,
})

df.to_csv("dataset.csv", index=False)